1.PrivacyNet: Semi-Adversarial Networks for Multi-attribute Face Privacy ⬇️
In recent years, the utilization of biometric information has become more and more common for various forms of identity verification and user authentication. However, as a consequence of the widespread use and storage of biometric information, concerns regarding sensitive information leakage and the protection of users' privacy have been raised. Recent research efforts targeted these concerns by proposing the Semi-Adversarial Networks (SAN) framework for imparting gender privacy to face images. The objective of SAN is to perturb face image data such that it cannot be reliably used by a gender classifier but can still be used by a face matcher for matching purposes. In this work, we propose a novel Generative Adversarial Networks-based SAN model, PrivacyNet, that is capable of imparting selective soft biometric privacy to multiple soft-biometric attributes such as gender, age, and race. While PrivacyNet is capable of perturbing different sources of soft biometric information reliably and simultaneously, it also allows users to choose to obfuscate specific attributes, while preserving others. The results from extensive experiments on five independent face image databases demonstrate the efficacy of our proposed model in imparting selective multi-attribute privacy to face images.
2.Lightweight Residual Densely Connected Convolutional Neural Network ⬇️
Extremely efficient convolutional neural network architectures are one of the most important requirements for limited computing power devices (such as embedded and mobile devices). Recently, some architectures have been proposed to overcome this limitation by considering specific hardware-software equipment. In this paper, the residual densely connected blocks are proposed to guaranty the deep supervision, efficient gradient flow, and feature reuse abilities of convolutional neural network. The proposed method decreases the cost of training and inference processes without using any special hardware-software equipment by just reducing the number of parameters and computational operations while achieving a feasible accuracy. Extensive experimental results demonstrate that the proposed architecture is more efficient than the AlexNet and VGGNet in terms of model size, required parameters, and even accuracy. The proposed model is evaluated on the ImageNet, MNIST, Fashion MNIST, SVHN, CIFAR-10, and CIFAR-100. It achieves state-of-the-art results on the Fashion MNIST dataset and reasonable results on the others. The obtained results show that the proposed model is superior to efficient models such as the SqueezNet and is also comparable with the state-of-the-art efficient models such as CondenseNet and ShuffleNet.
3.Using CNNs For Users Segmentation In Video See-Through Augmented Virtuality ⬇️
In this paper, we present preliminary results on the use of deep learning techniques to integrate the users self-body and other participants into a head-mounted video see-through augmented virtuality scenario. It has been previously shown that seeing users bodies in such simulations may improve the feeling of both self and social presence in the virtual environment, as well as user performance. We propose to use a convolutional neural network for real time semantic segmentation of users bodies in the stereoscopic RGB video streams acquired from the perspective of the user. We describe design issues as well as implementation details of the system and demonstrate the feasibility of using such neural networks for merging users bodies in an augmented virtuality simulation.
4.Butterfly detection and classification based on integrated YOLO algorithm ⬇️
Insects are abundant species on the earth, and the task of identification and identification of insects is complex and arduous. How to apply artificial intelligence technology and digital image processing methods to automatic identification of insect species is a hot issue in current research. In this paper, the problem of automatic detection and classification recognition of butterfly photographs is studied, and a method of bio-labeling suitable for butterfly classification is proposed. On the basis of YOLO algorithm, by synthesizing the results of YOLO models with different training mechanisms, a butterfly automatic detection and classification recognition algorithm based on YOLO algorithm is proposed. It greatly improves the generalization ability of YOLO algorithm and makes it have better ability to solve small sample problems. The experimental results show that the proposed annotation method and integrated YOLO algorithm have high accuracy and recognition rate in butterfly automatic detection and recognition.
5.First image then video: A two-stage network for spatiotemporal video denoising ⬇️
Video denoising is to remove noise from noise-corrupted data, thus recovering true signals via spatiotemporal processing. Existing approaches for spatiotemporal video denoising tend to suffer from motion blur artifacts, that is, the boundary of a moving object tends to appear blurry especially when the object undergoes a fast motion, causing optical flow calculation to break down. In this paper, we address this challenge by designing a first-image-then-video two-stage denoising neural network, consisting of an image denoising module for spatially reducing intra-frame noise followed by a regular spatiotemporal video denoising module. The intuition is simple yet powerful and effective: the first stage of image denoising effectively reduces the noise level and, therefore, allows the second stage of spatiotemporal denoising for better modeling and learning everywhere, including along the moving object boundaries. This two-stage network, when trained in an end-to-end fashion, yields the state-of-the-art performances on the video denoising benchmark Vimeo90K dataset in terms of both denoising quality and computation. It also enables an unsupervised approach that achieves comparable performance to existing supervised approaches.
6.Graph-FCN for image semantic segmentation ⬇️
Semantic segmentation with deep learning has achieved great progress in classifying the pixels in the image. However, the local location information is usually ignored in the high-level feature extraction by the deep learning, which is important for image semantic segmentation. To avoid this problem, we propose a graph model initialized by a fully convolutional network (FCN) named Graph-FCN for image semantic segmentation. Firstly, the image grid data is extended to graph structure data by a convolutional network, which transforms the semantic segmentation problem into a graph node classification problem. Then we apply graph convolutional network to solve this graph node classification problem. As far as we know, it is the first time that we apply the graph convolutional network in image semantic segmentation. Our method achieves competitive performance in mean intersection over union (mIOU) on the VOC dataset(about 1.34% improvement), compared to the original FCN model.
7.NAS-Bench-102: Extending the Scope of Reproducible Neural Architecture Search ⬇️
Neural architecture search (NAS) has achieved breakthrough success in a great number of applications in the past few years. It could be time to take a step back and analyze the good and bad aspects in the field of NAS. A variety of algorithms search architectures under different search space. These searched architectures are trained using different setups, e.g., hyper-parameters, data augmentation, regularization. This raises a comparability problem when comparing the performance of various NAS algorithms. NAS-Bench-101 has shown success to alleviate this problem. In this work, we propose an extension to NAS-Bench-101: NAS-Bench-102 with a different search space, results on multiple datasets, and more diagnostic information. NAS-Bench-102 has a fixed search space and provides a unified benchmark for almost any up-to-date NAS algorithms. The design of our search space is inspired from the one used in the most popular cell-based searching algorithms, where a cell is represented as a DAG. Each edge here is associated with an operation selected from a predefined operation set. For it to be applicable for all NAS algorithms, the search space defined in NAS-Bench-102 includes all possible architectures generated by 4 nodes and 5 associated operation options, which results in 15,625 candidates in total. The training log and the performance for each architecture candidate are provided for three datasets. This allows researchers to avoid unnecessary repetitive training for selected candidate and focus solely on the search algorithm itself. The training time saved for every candidate also largely improves the efficiency of many methods. We provide additional diagnostic information such as fine-grained loss and accuracy, which can give inspirations to new designs of NAS algorithms. In further support, we have analyzed it from many aspects and benchmarked 10 recent NAS algorithms.
8.BlendMask: Top-Down Meets Bottom-Up for Instance Segmentation ⬇️
Instance segmentation is one of the fundamental vision tasks. Recently, fully convolutional instance segmentation methods have drawn much attention as they are often simpler and more efficient than two-stage approaches like Mask R-CNN. To date, almost all such approaches fall behind the two-stage Mask R-CNN method in mask precision when models have similar computation complexity, leaving great room for improvement.
In this work, we achieve improved mask prediction by effectively combining instance-level information with semantic information with lower-level fine-granularity. Our main contribution is a blender module which draws inspiration from both top-down and bottom-up instance segmentation approaches. The proposed BlendMask can effectively predict dense per-pixel position-sensitive instance features with very few channels, and learn attention maps for each instance with merely one convolution layer, thus being fast in inference. BlendMask can be easily incorporated with the state-of-the-art one-stage detection frameworks and outperforms Mask R-CNN under the same training schedule while being 20% faster. A light-weight version of BlendMask achieves $ 34.2% $ mAP at 25 FPS evaluated on a single 1080Ti GPU card. Because of its simplicity and efficacy, we hope that our BlendMask could serve as a simple yet strong baseline for a wide range of instance-wise prediction tasks.
9.Video Cloze Procedure for Self-Supervised Spatio-Temporal Learning ⬇️
We propose a novel self-supervised method, referred to as Video Cloze Procedure (VCP), to learn rich spatial-temporal representations. VCP first generates "blanks" by withholding video clips and then creates "options" by applying spatio-temporal operations on the withheld clips. Finally, it fills the blanks with "options" and learns representations by predicting the categories of operations applied on the clips. VCP can act as either a proxy task or a target task in self-supervised learning. As a proxy task, it converts rich self-supervised representations into video clip operations (options), which enhances the flexibility and reduces the complexity of representation learning. As a target task, it can assess learned representation models in a uniform and interpretable manner. With VCP, we train spatial-temporal representation models (3D-CNNs) and apply such models on action recognition and video retrieval tasks. Experiments on commonly used benchmarks show that the trained models outperform the state-of-the-art self-supervised models with significant margins.
10.Video Saliency Prediction Using Enhanced Spatiotemporal Alignment Network ⬇️
Due to a variety of motions across different frames, it is highly challenging to learn an effective spatiotemporal representation for accurate video saliency prediction (VSP). To address this issue, we develop an effective spatiotemporal feature alignment network tailored to VSP, mainly including two key sub-networks: a multi-scale deformable convolutional alignment network (MDAN) and a bidirectional convolutional Long Short-Term Memory (Bi-ConvLSTM) network. The MDAN learns to align the features of the neighboring frames to the reference one in a coarse-to-fine manner, which can well handle various motions. Specifically, the MDAN owns a pyramidal feature hierarchy structure that first leverages deformable convolution (Dconv) to align the lower-resolution features across frames, and then aggregates the aligned features to align the higher-resolution features, progressively enhancing the features from top to bottom. The output of MDAN is then fed into the Bi-ConvLSTM for further enhancement, which captures the useful long-time temporal information along forward and backward timing directions to effectively guide attention orientation shift prediction under complex scene transformation. Finally, the enhanced features are decoded to generate the predicted saliency map. The proposed model is trained end-to-end without any intricate post processing. Extensive evaluations on four VSP benchmark datasets demonstrate that the proposed method achieves favorable performance against state-of-the-art methods. The source codes and all the results will be released.
11.ZeroQ: A Novel Zero Shot Quantization Framework ⬇️
Quantization is a promising approach for reducing the inference time and memory footprint of neural networks. However, most existing quantization methods require access to the original training dataset for retraining during quantization. This is often not possible for applications with sensitive or proprietary data, e.g., due to privacy and security concerns. Existing zero-shot quantization methods use different heuristics to address this, but they result in poor performance, especially when quantizing to ultra-low precision. Here, we propose ZeroQ , a novel zero-shot quantization framework to address this. ZeroQ enables mixed-precision quantization without any access to the training or validation data. This is achieved by optimizing for a Distilled Dataset, which is engineered to match the statistics of batch normalization across different layers of the network. ZeroQ supports both uniform and mixed-precision quantization. For the latter, we introduce a novel Pareto frontier based method to automatically determine the mixed-precision bit setting for all layers, with no manual search involved. We extensively test our proposed method on a diverse set of models, including ResNet18/50/152, MobileNetV2, ShuffleNet, SqueezeNext, and InceptionV3 on ImageNet, as well as RetinaNet-ResNet50 on the Microsoft COCO dataset. In particular, we show that ZeroQ can achieve 1.71% higher accuracy on MobileNetV2, as compared to the recently proposed DFQ method. Importantly, ZeroQ has a very low computational overhead, and it can finish the entire quantization process in less than 30s (0.5% of one epoch training time of ResNet50 on ImageNet). We have open-sourced the ZeroQ framework\footnote{this https URL}.
12.Low-Budget Unsupervised Label Query through Domain Alignment Enforcement ⬇️
Deep learning revolution happened thanks to the availability of a massive amount of labelled data which have contributed to the development of models with extraordinary inference capabilities. Despite the public availability of a large quantity of datasets, it is often necessary to generate a new set of labelled data to address specific requirements. In addition, the production of labels is costly and sometimes it requires a specific expertise to be fulfilled. In this work, we introduce a new problem called low budget unsupervised label query that consists in a model trained to suggests to the user a set of samples to be labelled, from a completely unlabelled dataset, to maximize the classification accuracy on that dataset. We propose to adopt a domain alignment model, modified to enforce consistency, to align a known dataset (source) and the dataset to be labelled (target). Finally, we propose a novel sample selection method based on uniform entropy sampling, named UNFOLD, which is deterministic and steadily outperforms other baselines as well as competing models on a large variety of publicly available datasets.
13.Multi-lane Detection Using Instance Segmentation and Attentive Voting ⬇️
Autonomous driving is becoming one of the leading industrial research areas. Therefore many automobile companies are coming up with semi to fully autonomous driving solutions. Among these solutions, lane detection is one of the vital driver-assist features that play a crucial role in the decision-making process of the autonomous vehicle. A variety of solutions have been proposed to detect lanes on the road, which ranges from using hand-crafted features to the state-of-the-art end-to-end trainable deep learning architectures. Most of these architectures are trained in a traffic constrained environment. In this paper, we propose a novel solution to multi-lane detection, which outperforms state of the art methods in terms of both accuracy and speed. To achieve this, we also offer a dataset with a more intuitive labeling scheme as compared to other benchmark datasets. Using our approach, we are able to obtain a lane segmentation accuracy of 99.87% running at 54.53 fps (average).
14.Multi-organ Segmentation over Partially Labeled Datasets with Multi-scale Feature Abstraction ⬇️
This paper presents a unified training strategy that enables a novel multi-scale deep neural network to be trained on multiple partially labeled datasets for multi-organ segmentation. Multi-scale contextual information is effective for pixel-level label prediction, i.e. image segmentation. However, such important information is only partially exploited by the existing methods. In this paper, we propose a new network architecture for multi-scale feature abstraction, which integrates pyramid feature analysis into an image segmentation model. To bridge the semantic gap caused by directly merging features from different scales, an equal convolutional depth mechanism is proposed. In addition, we develop a deep supervision mechanism for refining outputs in different scales. To fully leverage the segmentation features from different scales, we design an adaptive weighting layer to fuse the outputs in an automatic fashion. All these features together integrate into a pyramid-input pyramid-output network for efficient feature extraction. Last but not least, to alleviate the hunger for fully annotated data in training deep segmentation models, a unified training strategy is proposed to train one segmentation model on multiple partially labeled datasets for multi-organ segmentation with a novel target adaptive loss. Our proposed method was evaluated on four publicly available datasets, including BTCV, LiTS, KiTS and Spleen, where very promising performance has been achieved. The source code of this work is publicly shared at this https URL for others to easily reproduce the work and build their own models with the introduced mechanisms.
15.A Coarse-to-Fine Adaptive Network for Appearance-Based Gaze Estimation ⬇️
Human gaze is essential for various appealing applications. Aiming at more accurate gaze estimation, a series of recent works propose to utilize face and eye images simultaneously. Nevertheless, face and eye images only serve as independent or parallel feature sources in those works, the intrinsic correlation between their features is overlooked. In this paper we make the following contributions: 1) We propose a coarse-to-fine strategy which estimates a basic gaze direction from face image and refines it with corresponding residual predicted from eye images. 2) Guided by the proposed strategy, we design a framework which introduces a bi-gram model to bridge gaze residual and basic gaze direction, and an attention component to adaptively acquire suitable fine-grained feature. 3) Integrating the above innovations, we construct a coarse-to-fine adaptive network named CA-Net and achieve state-of-the-art performances on MPIIGaze and EyeDiap.
16.DeepFakes and Beyond: A Survey of Face Manipulation and Fake Detection ⬇️
The free access to large-scale public databases, together with the fast progress of deep learning techniques, in particular Generative Adversarial Networks, have led to the generation of very realistic fake contents with its corresponding implications towards society in this era of fake news. This survey provides a thorough review of techniques for manipulating face images including DeepFake methods, and methods to detect such manipulations. In particular, four types of facial manipulation are reviewed: i) entire face synthesis, ii) face identity swap (DeepFakes), iii) facial attributes manipulation, and iv) facial expression manipulation. For each manipulation type, we provide details regarding manipulation techniques, existing public databases, and key benchmarks for technology evaluation of fake detection methods, including a summary of results from those evaluations. Among the different databases available and discussed in the survey, FaceForensics++ is for example one of the most widely used for detecting both face identity swap and facial expression manipulations, with results in the literature in the range of 90-100% of manipulation detection accuracy.
In addition to the survey information, we also discuss trends and provide an outlook of the ongoing work in this field, e.g., the recently announced DeepFake Detection Challenge (DFDC).
17.Handwritten Optical Character Recognition (OCR): A Comprehensive Systematic Literature Review (SLR) ⬇️
Given the ubiquity of handwritten documents in human transactions, Optical Character Recognition (OCR) of documents have invaluable practical worth. Optical character recognition is a science that enables to translate various types of documents or images into analyzable, editable and searchable data. During last decade, researchers have used artificial intelligence / machine learning tools to automatically analyze handwritten and printed documents in order to convert them into electronic format. The objective of this review paper is to summarize research that has been conducted on character recognition of handwritten documents and to provide research directions. In this Systematic Literature Review (SLR) we collected, synthesized and analyzed research articles on the topic of handwritten OCR (and closely related topics) which were published between year 2000 to 2018. We followed widely used electronic databases by following pre-defined review protocol. Articles were searched using keywords, forward reference searching and backward reference searching in order to search all the articles related to the topic. After carefully following study selection process 142 articles were selected for this SLR. This review article serves the purpose of presenting state of the art results and techniques on OCR and also provide research directions by highlighting research gaps.
18.Erase and Restore: Simple, Accurate and Resilient Detection of $L_2$ Adversarial Examples ⬇️
By adding carefully crafted perturbations to input images, adversarial examples (AEs) can be generated to mislead neural-network-based image classifiers.
$L_2$ adversarial perturbations by Carlini and Wagner (CW) are regarded as among the most effective attacks. While many countermeasures against AEs have been proposed, detection of adaptive CW$L_2$ AEs has been very inaccurate. Our observation is that those deliberately altered pixels in an$L_2$ AE, altogether, exert their malicious influence. By randomly erasing some pixels from an$L_2$ AE and then restoring it with an inpainting technique, such an AE, before and after the steps, tends to have different classification results, while a benign sample does not show this symptom. Based on this, we propose a novel AE detection technique, Erase and Restore (E&R), that exploits the limitation of$L_2$ attacks. On two popular image datasets, CIFAR-10 and ImageNet, our experiments show that the proposed technique is able to detect over 98% of the AEs generated by CW and other$L_2$ algorithms and has a very low false positive rate on benign images. Moreover, our approach demonstrate strong resilience to adaptive attacks. While adding noises and inpainting each have been well studied, by combining them together, we deliver a simple, accurate and resilient detection technique against adaptive$L_2$ AEs.
19.HMM-guided frame querying for bandwidth-constrained video search ⬇️
We design an agent to search for frames of interest in video stored on a remote server, under bandwidth constraints. Using a convolutional neural network to score individual frames and a hidden Markov model to propagate predictions across frames, our agent accurately identifies temporal regions of interest based on sparse, strategically sampled frames. On a subset of the ImageNet-VID dataset, we demonstrate that using a hidden Markov model to interpolate between frame scores allows requests of 98% of frames to be omitted, without compromising frame-of-interest classification accuracy.
20.Physically Plausible Spectral Reconstruction from RGB Images ⬇️
Recently Convolutional Neural Networks (CNN) have been used to reconstruct hyperspectral information from RGB images. Moreover, this spectral reconstruction problem (SR) can often be solved with good (low) error. However, these methods are not physically plausible: that is when the recovered spectra are reintegrated with the underlying camera sensitivities, the resulting predicted RGB is not the same as the actual RGB, and sometimes this discrepancy can be large. The problem is further compounded by exposure change. Indeed, most learning-based SR models train for a fixed exposure setting and we show that this can result in poor performance when exposure varies.
In this paper we show how CNN learning can be extended so that physical plausibility is enforced and the problem resulting from changing exposures is mitigated. Our SR solution improves the state-of-the-art spectral recovery performance under varying exposure conditions while simultaneously ensuring physical plausibility (the recovered spectra reintegrate to the input RGBs exactly).
21.Kalman Filtering and Expectation Maximization for Multitemporal Spectral Unmixing ⬇️
The recent evolution of hyperspectral imaging technology and the proliferation of new emerging applications presses for the processing of multiple temporal hyperspectral images. In this work, we propose a novel spectral unmixing (SU) strategy using physically motivated parametric endmember representations to account for temporal spectral variability. By representing the multitemporal mixing process using a state-space formulation, we are able to exploit the Bayesian filtering machinery to estimate the endmember variability coefficients. Moreover, by assuming that the temporal variability of the abundances is small over short intervals, an efficient implementation of the expectation maximization (EM) algorithm is employed to estimate the abundances and the other model parameters. Simulation results indicate that the proposed strategy outperforms state-of-the-art multitemporal SU algorithms.
22.Restricting the Flow: Information Bottlenecks for Attribution ⬇️
Attribution methods provide insights into the decision-making of machine learning models like artificial neural networks. For a given input sample, they assign a relevance score to each individual input variable, such as the pixels of an image. In this work we adapt the information bottleneck concept for attribution. By adding noise to intermediate feature maps we restrict the flow of information and can quantify (in bits) how much information image regions provide. We compare our method against ten baselines using three different metrics on VGG-16 and ResNet-50, and find that our methods outperform all baselines in five out of six settings. The method's information-theoretic foundation provides an absolute frame of reference for attribution values (bits) and a guarantee that regions scored close to zero are not necessary for the network's decision.
23.Kernelized Support Tensor Train Machines ⬇️
Tensor, a multi-dimensional data structure, has been exploited recently in the machine learning community. Traditional machine learning approaches are vector- or matrix-based, and cannot handle tensorial data directly. In this paper, we propose a tensor train (TT)-based kernel technique for the first time, and apply it to the conventional support vector machine (SVM) for image classification. Specifically, we propose a kernelized support tensor train machine that accepts tensorial input and preserves the intrinsic kernel property. The main contributions are threefold. First, we propose a TT-based feature mapping procedure that maintains the TT structure in the feature space. Second, we demonstrate two ways to construct the TT-based kernel function while considering consistency with the TT inner product and preservation of information. Third, we show that it is possible to apply different kernel functions on different data modes. In principle, our method tensorizes the standard SVM on its input structure and kernel mapping scheme. Extensive experiments are performed on real-world tensor data, which demonstrates the superiority of the proposed scheme under few-sample high-dimensional inputs.
24.DuDoNet++: Encoding mask projection to reduce CT metal artifacts ⬇️
CT metal artifact reduction (MAR) is a notoriously challenging task because the artifacts are structured and non-local in the image domain. However, they are inherently local in the sinogram domain. DuDoNet is the state-of-the-art MAR algorithm which exploits the latter characteristic by learning to reduce artifacts in the sinogram and image domain jointly. By design, DuDoNet treats the metal-affected regions in sinogram as missing and replaces them with the surrogate data generated by a neural network. Since fine-grained details within the metal-affected regions are completely ignored, the artifact-reduced CT images by DuDoNet tend to be over-smoothed and distorted. In this work, we investigate the issue by theoretical derivation. We propose to address the problem by (1) retaining the metal-affected regions in sinogram and (2) replacing the binarized metal trace with the metal mask projection such that the geometry information of metal implants is encoded. Extensive experiments on simulated datasets and expert evaluations on clinical images demonstrate that our network called DuDoNet++ yields anatomically more precise artifact-reduced images than DuDoNet, especially when the metallic objects are large.
25.Joint Unsupervised Learning for the Vertebra Segmentation, Artifact Reduction and Modality Translation of CBCT Images ⬇️
We investigate the unsupervised learning of the vertebra segmentation, artifact reduction and modality translation of CBCT images. To this end, we formulate this problem under a unified framework that jointly addresses these three tasks and intensively leverages the knowledge sharing. The unsupervised learning of this framework is enabled by 1) a novel shape-aware artifact disentanglement network that supports different forms of image synthesis and vertebra segmentation and 2) a deliberate fusion of knowledge from an independent CT dataset. Specifically, the proposed framework takes a random pair of CBCT and CT images as the input, and manipulates the synthesis and segmentation via different combinations of the decodings of the disentangled latent codes. Then, by discovering various forms of consistencies between the synthesized images and segmented , the learning is achieved via self-learning from the given CBCT and CT images obviating the need for the paired (i.e., anatomically identical) groundtruth data. Extensive experiments on clinical CBCT and CT datasets show that the proposed approach performs significantly better than other state-of-the-art unsupervised methods trained independently for each task and, remarkably, the proposed approach achieves a dice coefficient of 0.879 for unsupervised CBCT vertebra segmentation.
26.A Generalized Deep Learning Framework for Whole-Slide Image Segmentation and Analysis ⬇️
Histopathology tissue analysis is considered the gold standard in cancer diagnosis and prognosis. Given the large size of these images and the increase in the number of potential cancer cases, an automated solution as an aid to histopathologists is highly desirable. In the recent past, deep learning-based techniques have provided state of the art results in a wide variety of image analysis tasks, including analysis of digitized slides. However, the size of images and variability in histopathology tasks makes it a challenge to develop an integrated framework for histopathology image analysis. We propose a deep learning-based framework for histopathology tissue analysis. We demonstrate the generalizability of our framework, including training and inference, on several open-source datasets, which include CAMELYON (breast cancer metastases), DigestPath (colon cancer), and PAIP (liver cancer) datasets. We discuss multiple types of uncertainties pertaining to data and model, namely aleatoric and epistemic, respectively. Simultaneously, we demonstrate our model generalization across different data distribution by evaluating some samples on TCGA data. On CAMELYON16 test data (n=139) for the task of lesion detection, the FROC score achieved was 0.86 and in the CAMELYON17 test-data (n=500) for the task of pN-staging the Cohen's kappa score achieved was 0.9090 (third in the open leaderboard). On DigestPath test data (n=212) for the task of tumor segmentation, a Dice score of 0.782 was achieved (fourth in the challenge). On PAIP test data (n=40) for the task of viable tumor segmentation, a Jaccard Index of 0.75 (third in the challenge) was achieved, and for viable tumor burden, a score of 0.633 was achieved (second in the challenge). Our entire framework and related documentation are freely available at GitHub and PyPi.
27.Histogram Layers for Texture Analysis ⬇️
We present a histogram layer for artificial neural networks (ANNs). An essential aspect of texture analysis is the extraction of features that describe the distribution of values in local spatial regions. The proposed histogram layer leverages the spatial distribution of features for texture analysis and parameters for the layer are estimated during backpropagation. We compare our method with state-of-the-art texture encoding methods such as the Deep Encoding Network (DEP) and Deep Texture Encoding Network (DeepTEN) on three texture datasets: (1) the Describable Texture Dataset (DTD); (2) an extension of the ground terrain in outdoor scenes (GTOS-mobile); (3) and a subset of the Materials in Context (MINC-2500) dataset. Results indicate that the inclusion of the proposed histogram layer improves performance. The source code for the histogram layer is publicly available.
28.Residual Block-based Multi-Label Classification and Localization Network with Integral Regression for Vertebrae Labeling ⬇️
Accurate identification and localization of the vertebrae in CT scans is a critical and standard preprocessing step for clinical spinal diagnosis and treatment. Existing methods are mainly based on the integration of multiple neural networks, and most of them use the Gaussian heat map to locate the vertebrae's centroid. However, the process of obtaining the vertebrae's centroid coordinates using heat maps is non-differentiable, so it is impossible to train the network to label the vertebrae directly. Therefore, for end-to-end differential training of vertebra coordinates on CT scans, a robust and accurate automatic vertebral labeling algorithm is proposed in this study. Firstly, a novel residual-based multi-label classification and localization network is developed, which can capture multi-scale features, but also utilize the residual module and skip connection to fuse the multi-level features. Secondly, to solve the problem that the process of finding coordinates is non-differentiable and the spatial structure is not destructible, integral regression module is used in the localization network. It combines the advantages of heat map representation and direct regression coordinates to achieve end-to-end training, and can be compatible with any key point detection methods of medical image based on heat map. Finally, multi-label classification of vertebrae is carried out, which use bidirectional long short term memory (Bi-LSTM) to enhance the learning of long contextual information to improve the classification performance. The proposed method is evaluated on a challenging dataset and the results are significantly better than the state-of-the-art methods (mean localization error <3mm).
29.A Total Variation Denoising Method Based on Median Filter and Phase Consistency ⬇️
The total variation method is widely used in image noise suppression. However, this method is easy to cause the loss of image details, and it is also sensitive to parameters such as iteration time. In this work, the total variation method has been modified using a diffusion rate adjuster based on the phase congruency and a fusion filter of median filter and phase consistency boundary, which is called the MPC-TV method. Experimental results indicate that MPC-TV method is effective in noise suppression, especially for the removing of speckle noise, and it can also improve the robustness of iteration time of TV method on noise with different variance.
30.Simulation of Skin Stretching around the Forehead Wrinkles in Rhytidectomy ⬇️
Objective: Skin stretching around the forehead wrinkles is an important method in rhytidectomy. Proper parameters are required to evaluate the surgical effect. In this paper, a simulation method was proposed to obtain the parameters. Methods: Three-dimensional point cloud data with a resolution of 50 {\mu}m were employed. First, a smooth supporting contour under the wrinkled forehead was generated via b-spline interpolation and extrapolation to constrain the deformation of the wrinkled zone. Then, based on the vector formed intrinsic finite element (VFIFE) algorithm, the simulation was implemented in Matlab for the deformation of wrinkled forehead skin in the stretching process. Finally, the stress distribution and the residual wrinkles of forehead skin were employed to evaluate the surgical effect. Results: Although the residual wrinkles are similar when forehead wrinkles are finitely stretched, their stress distribution changes greatly. This indicates that the stress distribution in the skin is effective to evaluate the surgical effect, and the forehead wrinkles are easily to be overstretched, which may lead to potential skin injuries. Conclusion: The simulation method can predict stress distribution and residual wrinkles after forehead wrinkle stretching surgery, which can be potentially used to control the surgical process and further reduce risks of skin injury.
31.PatDNN: Achieving Real-Time DNN Execution on Mobile Devices with Pattern-based Weight Pruning ⬇️
With the emergence of a spectrum of high-end mobile devices, many applications that formerly required desktop-level computation capability are being transferred to these devices. However, executing the inference of Deep Neural Networks (DNNs) is still challenging considering high computation and storage demands, specifically, if real-time performance with high accuracy is needed. Weight pruning of DNNs is proposed, but existing schemes represent two extremes in the design space: non-structured pruning is fine-grained, accurate, but not hardware friendly; structured pruning is coarse-grained, hardware-efficient, but with higher accuracy loss. In this paper, we introduce a new dimension, fine-grained pruning patterns inside the coarse-grained structures, revealing a previously unknown point in design space. With the higher accuracy enabled by fine-grained pruning patterns, the unique insight is to use the compiler to re-gain and guarantee high hardware efficiency. In other words, our method achieves the best of both worlds, and is desirable across theory/algorithm, compiler, and hardware levels. The proposed PatDNN is an end-to-end framework to efficiently execute DNN on mobile devices with the help of a novel model compression technique (pattern-based pruning based on extended ADMM solution framework) and a set of thorough architecture-aware compiler- and code generation-based optimizations (filter kernel reordering, compressed weight storage, register load redundancy elimination, and parameter auto-tuning). Evaluation results demonstrate that PatDNN outperforms three state-of-the-art end-to-end DNN frameworks, TensorFlow Lite, TVM, and Alibaba Mobile Neural Network with speedup up to 44.5x, 11.4x, and 7.1x, respectively, with no accuracy compromise. Real-time inference of representative large-scale DNNs (e.g., VGG-16, ResNet-50) can be achieved using mobile devices.
32.Protecting GANs against privacy attacks by preventing overfitting ⬇️
Generative Adversarial Networks (GANs) have made releasing of synthetic images a viable approach to share data without releasing the original dataset. It has been shown that such synthetic data can be used for a variety of downstream tasks such as training classifiers that would otherwise require the original dataset to be shared. However, recent work has shown that the GAN models and their synthetically generated data can be used to infer the training set membership by an adversary who has access to the entire dataset and some auxiliary information. Here we develop a new GAN architecture (privGAN) which provides protection against this mode of attack while leading to negligible loss in downstream performances. Our architecture explicitly prevents overfitting to the training set thereby providing implicit protection against white-box attacks. The main contributions of this paper are: i) we propose a novel GAN architecture that can generate synthetic data in a privacy preserving manner and demonstrate the effectiveness of our model against white--box attacks on several benchmark datasets, ii) we provide a theoretical understanding of the optimal solution of the GAN loss function, iii) we demonstrate on two common benchmark datasets that synthetic images generated by privGAN lead to negligible loss in downstream performance when compared against non--private GANs. While we have focosued on benchmarking privGAN exclusively of image datasets, the architecture of privGAN is not exclusive to image datasets and can be easily extended to other types of datasets.
33.Deep Learning Training with Simulated Approximate Multipliers ⬇️
This paper presents by simulation how approximate multipliers can be utilized to enhance the training performance of convolutional neural networks (CNNs). Approximate multipliers have significantly better performance in terms of speed, power, and area compared to exact multipliers. However, approximate multipliers have an inaccuracy which is defined in terms of the Mean Relative Error (MRE). To assess the applicability of approximate multipliers in enhancing CNN training performance, a simulation for the impact of approximate multipliers error on CNN training is presented. The paper demonstrates that using approximate multipliers for CNN training can significantly enhance the performance in terms of speed, power, and area at the cost of a small negative impact on the achieved accuracy. Additionally, the paper proposes a hybrid training method which mitigates this negative impact on the accuracy. Using the proposed hybrid method, the training can start using approximate multipliers then switches to exact multipliers for the last few epochs. Using this method, the performance benefits of approximate multipliers in terms of speed, power, and area can be attained for a large portion of the training stage. On the other hand, the negative impact on the accuracy is diminished by using the exact multipliers for the last epochs of training.
34.Non-rigid Registration Method between 3D CT Liver Data and 2D Ultrasonic Images based on Demons Model ⬇️
The non-rigid registration between CT data and ultrasonic images of liver can facilitate the diagnosis and treatment, which has been widely studied in recent years. To improve the registration accuracy of the Demons model on the non-rigid registration between 3D CT liver data and 2D ultrasonic images, a novel boundary extraction and enhancement method based on radial directional local intuitionistic fuzzy entropy in the polar coordinates has been put forward, and a new registration workflow has been provided. Experiments show that our method can acquire high-accuracy registration results. Experiments also show that the accuracy of the results of our method is higher than that of the original Demons method and the Demons method using simulated ultrasonic image by Field II. The operation time of our registration workflow is about 30 seconds, and it can be used in the surgery.
35.Quantum Adversarial Machine Learning ⬇️
Adversarial machine learning is an emerging field that focuses on studying vulnerabilities of machine learning approaches in adversarial settings and developing techniques accordingly to make learning robust to adversarial manipulations. It plays a vital role in various machine learning applications and has attracted tremendous attention across different communities recently. In this paper, we explore different adversarial scenarios in the context of quantum machine learning. We find that, similar to traditional classifiers based on classical neural networks, quantum learning systems are likewise vulnerable to crafted adversarial examples, independent of whether the input data is classical or quantum. In particular, we find that a quantum classifier that achieves nearly the state-of-the-art accuracy can be conclusively deceived by adversarial examples obtained via adding imperceptible perturbations to the original legitimate samples. This is explicitly demonstrated with quantum adversarial learning in different scenarios, including classifying real-life images (e.g., handwritten digit images in the dataset MNIST), learning phases of matter (such as, ferromagnetic/paramagnetic orders and symmetry protected topological phases), and classifying quantum data. Furthermore, we show that based on the information of the adversarial examples at hand, practical defense strategies can be designed to fight against a number of different attacks. Our results uncover the notable vulnerability of quantum machine learning systems to adversarial perturbations, which not only reveals a novel perspective in bridging machine learning and quantum physics in theory but also provides valuable guidance for practical applications of quantum classifiers based on both near-term and future quantum technologies.