1.Don't Judge an Object by Its Context: Learning to Overcome Contextual Bias ⬇️
Existing models often leverage co-occurrences between objects and their context to improve recognition accuracy. However, strongly relying on context risks a model's generalizability, especially when typical co-occurrence patterns are absent. This work focuses on addressing such contextual biases to improve the robustness of the learnt feature representations. Our goal is to accurately recognize a category in the absence of its context, without compromising on performance when it co-occurs with context. Our key idea is to decorrelate feature representations of a category from its co-occurring context. We achieve this by learning a feature subspace that explicitly represents categories occurring in the absence of context along side a joint feature subspace that represents both categories and context. Our very simple yet effective method is extensible to two multi-label tasks -- object and attribute classification. On 4 challenging datasets, we demonstrate the effectiveness of our method in reducing contextual bias.
2.Robust Facial Landmark Detection via Aggregation on Geometrically Manipulated Faces ⬇️
In this work, we present a practical approach to the problem of facial landmark detection. The proposed method can deal with large shape and appearance variations under the rich shape deformation. To handle the shape variations we equip our method with the aggregation of manipulated face images. The proposed framework generates different manipulated faces using only one given face image. The approach utilizes the fact that small but carefully crafted geometric manipulation in the input domain can fool deep face recognition models. We propose three different approaches to generate manipulated faces in which two of them perform the manipulations via adversarial attacks and the other one uses known transformations. Aggregating the manipulated faces provides a more robust landmark detection approach which is able to capture more important deformations and variations of the face shapes. Our approach is demonstrated its superiority compared to the state-of-the-art method on benchmark datasets AFLW, 300-W, and COFW.
3.Unpaired Multi-modal Segmentation via Knowledge Distillation ⬇️
Multi-modal learning is typically performed with network architectures containing modality-specific layers and shared layers, utilizing co-registered images of different modalities. We propose a novel learning scheme for unpaired cross-modality image segmentation, with a highly compact architecture achieving superior segmentation accuracy. In our method, we heavily reuse network parameters, by sharing all convolutional kernels across CT and MRI, and only employ modality-specific internal normalization layers which compute respective statistics. To effectively train such a highly compact model, we introduce a novel loss term inspired by knowledge distillation, by explicitly constraining the KL-divergence of our derived prediction distributions between modalities. We have extensively validated our approach on two multi-class segmentation problems: i) cardiac structure segmentation, and ii) abdominal organ segmentation. Different network settings, i.e., 2D dilated network and 3D U-net, are utilized to investigate our method's general efficacy. Experimental results on both tasks demonstrate that our novel multi-modal learning scheme consistently outperforms single-modal training and previous multi-modal approaches.
4.Compression of convolutional neural networks for high performance imagematching tasks on mobile devices ⬇️
Deep neural networks have demonstrated state-of-the-art performance for feature-based image matching through the advent of new large and diverse datasets. However, there has been little work on evaluating the computational cost, model size, and matching accuracy tradeoffs for these models. This paper explicitly addresses these practical constraints by considering state-of-the-art L2Net architecture. We observe a significant redundancy in the L2Net architecture, which we exploit through the use of depthwise separable layers and an efficient Tucker decomposition. We demonstrate that a combination of these methods is more effective, but still sacrifices the top-end accuracy. We therefore propose the Convolution-Depthwise-Pointwise (CDP) layer, which provides a means of interpolating between the standard and depthwise separable convolutions. With this proposed layer, we are able to achieve up to 8 times reduction in the number of parameters on the L2Net architecture, 13 times reduction in the computational complexity, while sacrificing less than 1% on the overall accuracy across the HPatches benchmarks. To further demonstrate the generalisation of this approach, we apply it to the SuperPoint model. We show that CDP layers improve upon the accuracy while using significantly less parameters and floating-point operations for inference.
5.STAViS: Spatio-Temporal AudioVisual Saliency Network ⬇️
We introduce STAViS, a spatio-temporal audiovisual saliency network that combines spatio-temporal visual and auditory information in order to efficiently address the problem of saliency estimation in videos. Our approach employs a single network that combines visual saliency and auditory features and learns to appropriately localize sound sources and to fuse the two saliencies in order to obtain a final saliency map. The network has been designed, trained end-to-end, and evaluated on six different databases that contain audiovisual eye-tracking data of a large variety of videos. We compare our method against 8 different state-of-the-art visual saliency models. Evaluation results across databases indicate that our STAViS model outperforms our visual only variant as well as the other state-of-the-art models in the majority of cases. Also, the consistently good performance it achieves for all databases indicates that it is appropriate for estimating saliency "in-the-wild".
6.Virtual to Real adaptation of Pedestrian Detectors for Smart Cities ⬇️
Pedestrian detection through computer vision is a building block for a multitude of applications in the context of smart cities, such as surveillance of sensitive areas, personal safety, monitoring, and control of pedestrian flow, to mention only a few. Recently, there was an increasing interest in deep learning architectures for performing such a task. One of the critical objectives of these algorithms is to generalize the knowledge gained during the training phase to new scenarios having various characteristics, and a suitably labeled dataset is fundamental to achieve this goal. The main problem is that manually annotating a dataset usually requires a lot of human effort, and it is a time-consuming operation. For this reason, in this work, we introduced ViPeD - Virtual Pedestrian Dataset, a new synthetically generated set of images collected from a realistic 3D video game where the labels can be automatically generated exploiting 2D pedestrian positions extracted from the graphics engine. We used this new synthetic dataset training a state-of-the-art computationally-efficient Convolutional Neural Network (CNN) that is ready to be installed in smart low-power devices, like smart cameras. We addressed the problem of the domain-adaptation from the virtual world to the real one by fine-tuning the CNN using the synthetic data and also exploiting a mixed-batch supervised training approach. Extensive experimentation carried out on different real-world datasets shows very competitive results compared to other methods presented in the literature in which the algorithms are trained using real-world data.
7.DeeperForensics-1.0: A Large-Scale Dataset for Real-World Face Forgery Detection ⬇️
In this paper, we present our on-going effort of constructing a large-scale benchmark, DeeperForensics-1.0, for face forgery detection. Our benchmark represents the largest face forgery detection dataset by far, with 60, 000 videos constituted by a total of 17.6 million frames, 10 times larger than existing datasets of the same kind. Extensive real-world perturbations are applied to obtain a more challenging benchmark of larger scale and higher diversity. All source videos in DeeperForensics-1.0 are carefully collected, and fake videos are generated by a newly proposed end-to-end face swapping framework. The quality of generated videos outperforms those in existing datasets, validated by user studies. The benchmark features a hidden test set, which contains manipulated videos achieving high deceptive scores in human evaluations. We further contribute a comprehensive study that evaluates five representative detection baselines and make a thorough analysis of different settings. We believe this dataset will contribute to real-world face forgery detection research.
8.Spherical Image Generation from a Single Normal Field of View Image by Considering Scene Symmetry ⬇️
Spherical images taken in all directions (360 degrees) allow representing the surroundings of the subject and the space itself, providing an immersive experience to the viewers. Generating a spherical image from a single normal-field-of-view (NFOV) image is convenient and considerably expands the usage scenarios because there is no need to use a specific panoramic camera or take images from multiple directions; however, it is still a challenging and unsolved problem. The primary challenge is controlling the high degree of freedom involved in generating a wide area that includes the all directions of the desired plausible spherical image. On the other hand, scene symmetry is a basic property of the global structure of the spherical images, such as rotation symmetry, plane symmetry and asymmetry. We propose a method to generate spherical image from a single NFOV image, and control the degree of freedom of the generated regions using scene symmetry. We incorporate scene-symmetry parameters as latent variables into conditional variational autoencoders, following which we learn the conditional probability of spherical images for NFOV images and scene symmetry. Furthermore, the probability density functions are represented using neural networks, and scene symmetry is implemented using both circular shift and flip of the hidden variables. Our experiments show that the proposed method can generate various plausible spherical images, controlled from symmetric to asymmetric.
9.Objects detection for remote sensing images based on polar coordinates ⬇️
Oriented and horizontal bounding box are two typical output forms in the field of remote sensing object detection. In this filed, most present state-of-the-art detectors belong to anchor-based method and perform regression tasks in Cartesian coordinates, which cause the design of oriented detectors is much more complicated than the horizontal ones, because the former usually needs to devise more complex rotated anchors, rotated Intersection-over-Union (IOU) and rotated Non Maximum Supression (NMS). In this paper, we propose a novel anchor-free detector modeled in polar coordinates to detect objects for remote sensing images, which makes the acquisition of oriented output form be as simple as the horizontal one. Our model, named Polar Remote Sensing Object Detector (P-RSDet), takes the center point of each object as the pole point and the horizontal positive direction as the polar axis to establish the polar coordinate system. The detection of one object can be regarded as predictions of one polar radius and two polar angles for both horizontal and oriented bounding box by our model. P-RSDet realizes the combination of two output forms with minimum cost. Experiments show that our P-RSDet achieves competitive performances on DOTA, UCAS-AOD and NWPU VHR-10 datasets on both horizontal and oreinted detection fileds.
10.Generative Pseudo-label Refinement for Unsupervised Domain Adaptation ⬇️
We investigate and characterize the inherent resilience of conditional Generative Adversarial Networks (cGANs) against noise in their conditioning labels, and exploit this fact in the context of Unsupervised Domain Adaptation (UDA). In UDA, a classifier trained on the labelled source set can be used to infer pseudo-labels on the unlabelled target set. However, this will result in a significant amount of misclassified examples (due to the well-known domain shift issue), which can be interpreted as noise injection in the ground-truth labels for the target set. We show that cGANs are, to some extent, robust against such "shift noise". Indeed, cGANs trained with noisy pseudo-labels, are able to filter such noise and generate cleaner target samples. We exploit this finding in an iterative procedure where a generative model and a classifier are jointly trained: in turn, the generator allows to sample cleaner data from the target distribution, and the classifier allows to associate better labels to target samples, progressively refining target pseudo-labels. Results on common benchmarks show that our method performs better or comparably with the unsupervised domain adaptation state of the art.
11.Towards Coding for Human and Machine Vision: A Scalable Image Coding Approach ⬇️
The past decades have witnessed the rapid development of image and video coding techniques in the era of big data. However, the signal fidelity-driven coding pipeline design limits the capability of the existing image/video coding frameworks to fulfill the needs of both machine and human vision. In this paper, we come up with a novel image coding framework by leveraging both the compressive and the generative models, to support machine vision and human perception tasks jointly. Given an input image, the feature analysis is first applied, and then the generative model is employed to perform image reconstruction with features and additional reference pixels, in which compact edge maps are extracted in this work to connect both kinds of vision in a scalable way. The compact edge map serves as the basic layer for machine vision tasks, and the reference pixels act as a sort of enhanced layer to guarantee signal fidelity for human vision. By introducing advanced generative models, we train a flexible network to reconstruct images from compact feature representations and the reference pixels. Experimental results demonstrate the superiority of our framework in both human visual quality and facial landmark detection, which provide useful evidence on the emerging standardization efforts on MPEG VCM (Video Coding for Machine).
12.Fast Adaptation to Super-Resolution Networks via Meta-Learning ⬇️
Conventional supervised super-resolution (SR) approaches are trained with massive external SR datasets but fail to exploit desirable properties of the given test image. On the other hand, self-supervised SR approaches utilize the internal information within a test image but suffer from computational complexity in run-time. In this work, we observe the opportunity for further improvement of the performance of SISR without changing the architecture of conventional SR networks by practically exploiting additional information given from the input image. In the training stage, we train the network via meta-learning; thus, the network can quickly adapt to any input image at test time. Then, in the test stage, parameters of this meta-learned network are rapidly fine-tuned with only a few iterations by only using the given low-resolution image. The adaptation at the test time takes full advantage of patch-recurrence property observed in natural images. Our method effectively handles unknown SR kernels and can be applied to any existing model. We demonstrate that the proposed model-agnostic approach consistently improves the performance of conventional SR networks on various benchmark SR datasets.
13.Self-Supervised Fast Adaptation for Denoising via Meta-Learning ⬇️
Under certain statistical assumptions of noise, recent self-supervised approaches for denoising have been introduced to learn network parameters without true clean images, and these methods can restore an image by exploiting information available from the given input (i.e., internal statistics) at test time. However, self-supervised methods are not yet combined with conventional supervised denoising methods which train the denoising networks with a large number of external training samples. Thus, we propose a new denoising approach that can greatly outperform the state-of-the-art supervised denoising methods by adapting their network parameters to the given input through selfsupervision without changing the networks architectures. Moreover, we propose a meta-learning algorithm to enable quick adaptation of parameters to the specific input at test time. We demonstrate that the proposed method can be easily employed with state-of-the-art denoising networks without additional parameters, and achieve state-of-the-art performance on numerous benchmark datasets.
14.Deep Plastic Surgery: Robust and Controllable Image Editing with Human-Drawn Sketches ⬇️
Sketch-based image editing aims to synthesize and modify photos based on the structural information provided by the human-drawn sketches. Since sketches are difficult to collect, previous methods mainly use edge maps instead of sketches to train models (referred to as edge-based models). However, sketches display great structural discrepancy with edge maps, thus failing edge-based models. Moreover, sketches often demonstrate huge variety among different users, demanding even higher generalizability and robustness for the editing model to work. In this paper, we propose Deep Plastic Surgery, a novel, robust and controllable image editing framework that allows users to interactively edit images using hand-drawn sketch inputs. We present a sketch refinement strategy, as inspired by the coarse-to-fine drawing process of the artists, which we show can help our model well adapt to casual and varied sketches without the need for real sketch training data. Our model further provides a refinement level control parameter that enables users to flexibly define how "reliable" the input sketch should be considered for the final output, balancing between sketch faithfulness and output verisimilitude (as the two goals might contradict if the input sketch is drawn poorly). To achieve the multi-level refinement, we introduce a style-based module for level conditioning, which allows adaptive feature representations for different levels in a singe network. Extensive experimental results demonstrate the superiority of our approach in improving the visual quality and user controllablity of image editing over the state-of-the-art methods.
15.HMANet: Hybrid Multiple Attention Network for Semantic Segmentation in Aerial Images ⬇️
Semantic segmentation in very high resolution (VHR) aerial images is one of the most challenging tasks in remote sensing image understanding. Most of the current approaches are based on deep convolutional neural networks (DCNNs) for its remarkable ability of feature representations. Specifically, attention-based methods can effectively capture long-range dependencies and further reconstruct the feature maps for better representation. However, limited by the mere perspective of spacial and channel attention and huge computation complexity of self-attention mechanism, it's unlikely to model the effective semantic interdependencies between each pixel-pair. In this work, we propose a novel attention-based framework named Hybrid Multiple Attention Network (HMANet) to adaptively capture global correlations from the perspective of space, channel and category in a more effective and efficient manner. Concretely, a class augmented attention (CAA) module embedded with a class channel attention (CCA) module can be used to compute category-based correlation and recalibrate the class-level information. Additionally, we introduce a simple yet region shuffle attention (RSA) module to reduce feature redundant and improve the efficiency of self-attention mechanism via region-wise representations. Extensive experimental results on the ISPRS Vaihingen and Potsdam benchmark demonstrate the effectiveness and efficiency of our HMANet over other state-of-the-art methods.
16.Semi-supervised Learning via Conditional Rotation Angle Estimation ⬇️
Self-supervised learning (SlfSL), aiming at learning feature representations through ingeniously designed pretext tasks without human annotation, has achieved compelling progress in the past few years. Very recently, SlfSL has also been identified as a promising solution for semi-supervised learning (SemSL) since it offers a new paradigm to utilize unlabeled data. This work further explores this direction by proposing to couple SlfSL with SemSL. Our insight is that the prediction target in SemSL can be modeled as the latent factor in the predictor for the SlfSL target. Marginalizing over the latent factor naturally derives a new formulation which marries the prediction targets of these two learning processes. By implementing this idea through a simple-but-effective SlfSL approach -- rotation angle prediction, we create a new SemSL approach called Conditional Rotation Angle Estimation (CRAE). Specifically, CRAE is featured by adopting a module which predicts the image rotation angle conditioned on the candidate image class. Through experimental evaluation, we show that CRAE achieves superior performance over the other existing ways of combining SlfSL and SemSL. To further boost CRAE, we propose two extensions to strengthen the coupling between SemSL target and SlfSL target in basic CRAE. We show that this leads to an improved CRAE method which can achieve the state-of-the-art SemSL performance.
17.A novel tree-structured point cloud dataset for skeletonization algorithm evaluation ⬇️
Curve skeleton extraction from unorganized point cloud is a fundamental task of computer vision and three-dimensional data preprocessing and visualization. A great amount of work has been done to extract skeleton from point cloud. but the lack of standard datasets of point cloud with ground truth skeleton makes it difficult to evaluate these algorithms. In this paper, we construct a brand new tree-structured point cloud dataset, including ground truth skeletons, and point cloud models. In addition, four types of point cloud are built on clean point cloud: point clouds with noise, point clouds with missing data, point clouds with different density, and point clouds with uneven density distribution. We first use tree editor to build the tree skeleton and corresponding mesh model. Since the implicit surface is sufficiently expressive to retain the edges and details of the complex branches model, we use the implicit surface to model the triangular mesh. With the implicit surface, virtual scanner is applied to the sampling of point cloud. Finally, considering the challenges in skeleton extraction, we introduce different methods to build four different types of point cloud models. This dataset can be used as standard dataset for skeleton extraction algorithms. And the evaluation between skeleton extraction algorithms can be performed by comparing the ground truth skeleton with the extracted skeleton.
18.Multi-Scale Weight Sharing Network for Image Recognition ⬇️
In this paper, we explore the idea of weight sharing over multiple scales in convolutional networks. Inspired by traditional computer vision approaches, we share the weights of convolution kernels over different scales in the same layers of the network. Although multi-scale feature aggregation and sharing inside convolutional networks are common in practice, none of the previous works address the issue of convolutional weight sharing. We evaluate our weight sharing scheme on two heterogeneous image recognition datasets - ImageNet (object recognition) and Places365-Standard (scene classification). With approximately 25% fewer parameters, our shared-weight ResNet model provides similar performance compared to baseline ResNets. Shared-weight models are further validated via transfer learning experiments on four additional image recognition datasets - Caltech256 and Stanford 40 Actions (object-centric) and SUN397 and MIT Inddor67 (scene-centric). Experimental results demonstrate significant redundancy in the vanilla implementations of the deeper networks, and also indicate that a shift towards increasing the receptive field per parameter may improve future convolutional network architectures.
19.Learning landmark guided embeddings for animal re-identification ⬇️
Re-identification of individual animals in images can be ambiguous due to subtle variations in body markings between different individuals and no constraints on the poses of animals in the wild. Person re-identification is a similar task and it has been approached with a deep convolutional neural network (CNN) that learns discriminative embeddings for images of people. However, learning discriminative features for an individual animal is more challenging than for a person's appearance due to the relatively small size of ecological datasets compared to labelled datasets of person's identities. We propose to improve embedding learning by exploiting body landmarks information explicitly. Body landmarks are provided to the input of a CNN as confidence heatmaps that can be obtained from a separate body landmark predictor. The model is encouraged to use heatmaps by learning an auxiliary task of reconstructing input heatmaps. Body landmarks guide a feature extraction network to learn the representation of a distinctive pattern and its position on the body. We evaluate the proposed method on a large synthetic dataset and a small real dataset. Our method outperforms the same model without body landmarks input by 26% and 18% on the synthetic and the real datasets respectively. The method is robust to noise in input coordinates and can tolerate an error in coordinates up to 10% of the image size.
20.Neural Data Server: A Large-Scale Search Engine for Transfer Learning Data ⬇️
Transfer learning has proven to be a successful technique to train deep learning models in the domains where little training data is available. The dominant approach is to pretrain a model on a large generic dataset such as ImageNet and finetune its weights on the target domain. However, in the new era of an ever-increasing number of massive datasets, selecting the relevant data for pretraining is a critical issue. We introduce Neural Data Server (NDS), a large-scale search engine for finding the most useful transfer learning data to the target domain. Our NDS consists of a dataserver which indexes several large popular image datasets, and aims to recommend data to a client, an end-user with a target application with its own small labeled dataset. As in any search engine that serves information to possibly numerous users, we want the online computation performed by the dataserver to be minimal. The dataserver represents large datasets with a much more compact mixture-of experts model, and employs it to perform data search in a series of dataserver-client transactions at a low computational cost. We show the effectiveness of NDS in various transfer learning scenarios, demonstrating state-of-the-art performance on several target datasets and tasks such as image classification, object detection and instance segmentation. Our Neural Data Server is available as a web-service at this http URL, recommending data to users with the aim to improve performance of their A.I. application.
21.Toward Generalized Clustering through an One-Dimensional Approach ⬇️
After generalizing the concept of clusters to incorporate clusters that are linked to other clusters through some relatively narrow bridges, an approach for detecting patches of separation between these clusters is developed based on an agglomerative clustering, more specifically the single-linkage, applied to one-dimensional slices obtained from respective feature spaces. The potential of this method is illustrated with respect to the analyses of clusterless uniform and normal distributions of points, as well as a one-dimensional clustering model characterized by two intervals with high density of points separated by a less dense interstice. This partial clustering method is then considered as a means of feature selection and cluster identification, and two simple but potentially effective respective methods are described and illustrated with respect to some hypothetical situations.
22.Investigating the Impact of Inclusion in Face Recognition Training Data on Individual Face Identification ⬇️
Modern face recognition systems leverage datasets containing images of hundreds of thousands of specific individuals' faces to train deep convolutional neural networks to learn an embedding space that maps an arbitrary individual's face to a vector representation of their identity. The performance of a face recognition system in face verification (1:1) and face identification (1:N) tasks is directly related to the ability of an embedding space to discriminate between identities. Recently, there has been significant public scrutiny into the source and privacy implications of large-scale face recognition training datasets such as MS-Celeb-1M and MegaFace, as many people are uncomfortable with their face being used to train dual-use technologies that can enable mass surveillance. However, the impact of an individual's inclusion in training data on a derived system's ability to recognize them has not previously been studied. In this work, we audit ArcFace, a state-of-the-art, open source face recognition system, in a large-scale face identification experiment with more than one million distractor images. We find a Rank-1 face identification accuracy of 79.71% for individuals present in the model's training data and an accuracy of 75.73% for those not present. This modest difference in accuracy demonstrates that face recognition systems using deep learning work better for individuals they are trained on, which has serious privacy implications when one considers all major open source face recognition training datasets do not obtain informed consent from individuals during their collection.
23.An Emerging Coding Paradigm VCM: A Scalable Coding Approach Beyond Feature and Signal ⬇️
In this paper, we study a new problem arising from the emerging MPEG standardization effort Video Coding for Machine (VCM), which aims to bridge the gap between visual feature compression and classical video coding. VCM is committed to address the requirement of compact signal representation for both machine and human vision in a more or less scalable way. To this end, we make endeavors in leveraging the strength of predictive and generative models to support advanced compression techniques for both machine and human vision tasks simultaneously, in which visual features serve as a bridge to connect signal-level and task-level compact representations in a scalable manner. Specifically, we employ a conditional deep generation network to reconstruct video frames with the guidance of learned motion pattern. By learning to extract sparse motion pattern via a predictive model, the network elegantly leverages the feature representation to generate the appearance of to-be-coded frames via a generative model, relying on the appearance of the coded key frames. Meanwhile, the sparse motion pattern is compact and highly effective for high-level vision tasks, e.g. action recognition. Experimental results demonstrate that our method yields much better reconstruction quality compared with the traditional video codecs (0.0063 gain in SSIM), as well as state-of-the-art action recognition performance over highly compressed videos (9.4% gain in recognition accuracy), which showcases a promising paradigm of coding signal for both human and machine vision.
24.An inexact matching approach for the comparison of plane curves with general elastic metrics ⬇️
This paper introduces a new mathematical formulation and numerical approach for the computation of distances and geodesics between immersed planar curves. Our approach combines the general simplifying transform for first-order elastic metrics that was recently introduced by Kurtek and Needham, together with a relaxation of the matching constraint using parametrization-invariant fidelity metrics. The main advantages of this formulation are that it leads to a simple optimization problem for discretized curves, and that it provides a flexible approach to deal with noisy, inconsistent or corrupted data. These benefits are illustrated via a few preliminary numerical results.
25.An Internal Covariate Shift Bounding Algorithm for Deep Neural Networks by Unitizing Layers' Outputs ⬇️
Batch Normalization (BN) techniques have been proposed to reduce the so-called Internal Covariate Shift (ICS) by attempting to keep the distributions of layer outputs unchanged. Experiments have shown their effectiveness on training deep neural networks. However, since only the first two moments are controlled in these BN techniques, it seems that a weak constraint is imposed on layer distributions and furthermore whether such constraint can reduce ICS is unknown. Thus this paper proposes a measure for ICS by using the Earth Mover (EM) distance and then derives the upper and lower bounds for the measure to provide a theoretical analysis of BN. The upper bound has shown that BN techniques can control ICS only for the outputs with low dimensions and small noise whereas their control is NOT effective in other cases. This paper also proves that such control is just a bounding of ICS rather than a reduction of ICS. Meanwhile, the analysis shows that the high-order moments and noise, which BN cannot control, have great impact on the lower bound. Based on such analysis, this paper furthermore proposes an algorithm that unitizes the outputs with an adjustable parameter to further bound ICS in order to cope with the problems of BN. The upper bound for the proposed unitization is noise-free and only dominated by the parameter. Thus, the parameter can be trained to tune the bound and further to control ICS. Besides, the unitization is embedded into the framework of BN to reduce the information loss. The experiments show that this proposed algorithm outperforms existing BN techniques on CIFAR-10, CIFAR-100 and ImageNet datasets.
26.Explainable Deep Convolutional Candlestick Learner ⬇️
Candlesticks are graphical representations of price movements for a given period. The traders can discovery the trend of the asset by looking at the candlestick patterns. Although deep convolutional neural networks have achieved great success for recognizing the candlestick patterns, their reasoning hides inside a black box. The traders cannot make sure what the model has learned. In this contribution, we provide a framework which is to explain the reasoning of the learned model determining the specific candlestick patterns of time series. Based on the local search adversarial attacks, we show that the learned model perceives the pattern of the candlesticks in a way similar to the human trader.
27.Learning Generative Models using Denoising Density Estimators ⬇️
Learning generative probabilistic models that can estimate the continuous density given a set of samples, and that can sample from that density, is one of the fundamental challenges in unsupervised machine learning. In this paper we introduce a new approach to obtain such models based on what we call denoising density estimators (DDEs). A DDE is a scalar function, parameterized by a neural network, that is efficiently trained to represent a kernel density estimator of the data. Leveraging DDEs, our main contribution is to develop a novel approach to obtain generative models that sample from given densities. We prove that our algorithms to obtain both DDEs and generative models are guaranteed to converge to the correct solutions. Advantages of our approach include that we do not require specific network architectures like in normalizing flows, ordinary differential equation solvers as in continuous normalizing flows, nor do we require adversarial training as in generative adversarial networks (GANs). Finally, we provide experimental results that demonstrate practical applications of our technique.