1.Dynamic Task Weighting Methods for Multi-task Networks in Autonomous Driving Systems ⬇️
Deep multi-task networks are of particular interest for autonomous driving systems. They can potentially strike an excellent trade-off between predictive performance, hardware constraints and efficient use of information from multiple types of annotations and modalities. However, training such models is non-trivial and requires balancing the learning of all tasks as their respective losses display different scales, ranges and dynamics across training. Multiple task weighting methods that adjust the losses in an adaptive way have been proposed recently on different datasets and combinations of tasks, making it difficult to compare them. In this work, we review and systematically evaluate nine task weighting strategies on common grounds on three automotive datasets (KITTI, Cityscapes and WoodScape). We then propose a novel method combining evolutionary meta-learning and task-based selective backpropagation, for finding the task weights and training the network reliably. Our method outperforms state-of-the-art methods by
$3%$ on a two-task application.
2.DAF-NET: a saliency based weakly supervised method of dual attention fusion for fine-grained image classification ⬇️
Fine-grained image classification is a challenging problem, since the difficulty of finding discriminative features. To handle this circumstance, basically, there are two ways to go. One is use attention based method to focus on informative areas, while the other one aims to find high order between features. Further, for attention based method there are two directions, activation based and detection based, which are proved effective by scholars. However ,rare work focus on fusing two types of attention with high order feature. In this paper, we propose a novel DAF method which fuse two types of attention and use them to as PAF(part attention filter) in deep bilinear transformation module to mine the relationship between separate parts of an object. Briefly, our network constructed by a student net who attempt to output two attention maps and a teacher net uses these two maps as empirical information to refine the result. The experiment result shows that only student net could get 87.6% accuracy in CUB dataset while cooperating with teacher net could achieve 89.1% accuracy.
3.An Exploration of Embodied Visual Exploration ⬇️
Embodied computer vision considers perception for robots in general, unstructured environments. Of particular importance is the embodied visual exploration problem: how might a robot equipped with a camera scope out a new environment? Despite the progress thus far, many basic questions pertinent to this problem remain unanswered: (i) What does it mean for an agent to explore its environment well? (ii) Which methods work well, and under which assumptions and environmental settings? (iii) Where do current approaches fall short, and where might future work seek to improve? Seeking answers to these questions, we perform a thorough empirical study of four state-of-the-art paradigms on two photorealistic simulated 3D environments. We present a taxonomy of key exploration methods and a standard framework for benchmarking visual exploration algorithms. Our experimental results offer insights, and suggest new performance metrics and baselines for future work in visual exploration.
4.Trained Trajectory based Automated Parking System using Visual SLAM ⬇️
Automated Parking is becoming a standard feature in modern vehicles. Existing parking systems build a local map to be able to plan for maneuvering towards a detected slot. Next generation parking systems have an use case where they build a persistent map of the environment where the car is frequently parked, say for example, home parking or office parking. The pre-built map helps in re-localizing the vehicle better when its trying to park the next time. This is achieved by augmenting the parking system with a Visual SLAM pipeline and the feature is called trained trajectory parking. In this paper, we discuss the use cases, design and implementation of a trained trajectory automated parking system. To encourage further research, we release a dataset of 50 video sequences comprising of over 100,000 images with the associated ground truth as a companion to our WoodScape dataset \cite{Yogamani_2019_ICCV}. To the best of the authors' knowledge, this is the first public dataset for trained trajectory parking system scenarios.
5.Inferring Convolutional Neural Networks' accuracies from their architectural characterizations ⬇️
Convolutional Neural Networks (CNNs) have shown strong promise for analyzing scientific data from many domains including particle imaging detectors. However, the challenge of choosing the appropriate network architecture (depth, kernel shapes, activation functions, etc.) for specific applications and different data sets is still poorly understood. In this paper, we study the relationships between a CNN's architecture and its performance by proposing a systematic language that is useful for comparison between different CNN's architectures before training time. We characterize CNN's architecture by different attributes, and demonstrate that the attributes can be predictive of the networks' performance in two specific computer vision-based physics problems -- event vertex finding and hadron multiplicity classification in the MINERvA experiment at Fermi National Accelerator Laboratory. In doing so, we extract several architectural attributes from optimized networks' architecture for the physics problems, which are outputs of a model selection algorithm called Multi-node Evolutionary Neural Networks for Deep Learning (MENNDL). We use machine learning models to predict whether a network can perform better than a certain threshold accuracy before training. The models perform 16-20% better than random guessing. Additionally, we found an coefficient of determination of 0.966 for an Ordinary Least Squares model in a regression on accuracy over a large population of networks.
6.General 3D Room Layout from a Single View by Render-and-Compare ⬇️
We present a novel method to reconstruct the 3D layout of a room -- walls,floors, ceilings -- from a single perspective view, even for the case of general configurations. This input view can consist of a color image only, but considering a depth map will result in a more accurate reconstruction. Our approach is based on solving a constrained discrete optimization problem, which selects the polygons which are part of the layout from a large set of potential polygons. In order to deal with occlusions between components of the layout, which is a problem ignored by previous works, we introduce an analysis-by-synthesis method to iteratively refine the 3D layout estimate. To the best of our knowledge, our method is the first that can estimate a layout in such general conditions from a single view. We additionally introduce a new annotation dataset made of 91 images from the ScanNet dataset and several metrics, in order to evaluate our results quantitatively.
7.Deep Video Super-Resolution using HR Optical Flow Estimation ⬇️
Video super-resolution (SR) aims at generating a sequence of high-resolution (HR) frames with plausible and temporally consistent details from their low-resolution (LR) counterparts. The key challenge for video SR lies in the effective exploitation of temporal dependency between consecutive frames. Existing deep learning based methods commonly estimate optical flows between LR frames to provide temporal dependency. However, the resolution conflict between LR optical flows and HR outputs hinders the recovery of fine details. In this paper, we propose an end-to-end video SR network to super-resolve both optical flows and images. Optical flow SR from LR frames provides accurate temporal dependency and ultimately improves video SR performance. Specifically, we first propose an optical flow reconstruction network (OFRnet) to infer HR optical flows in a coarse-to-fine manner. Then, motion compensation is performed using HR optical flows to encode temporal dependency. Finally, compensated LR inputs are fed to a super-resolution network (SRnet) to generate SR results. Extensive experiments have been conducted to demonstrate the effectiveness of HR optical flows for SR performance improvement. Comparative results on the Vid4 and DAVIS-10 datasets show that our network achieves the state-of-the-art performance.
8.State Transition Modeling of the Smoking Behavior using LSTM Recurrent Neural Networks ⬇️
The use of sensors has pervaded everyday life in several applications including human activity monitoring, healthcare, and social networks. In this study, we focus on the use of smartwatch sensors to recognize smoking activity. More specifically, we have reformulated the previous work in detection of smoking to include in-context recognition of smoking. Our presented reformulation of the smoking gesture as a state-transition model that consists of the mini-gestures hand-to-lip, hand-on-lip, and hand-off-lip, has demonstrated improvement in detection rates nearing 100% using conventional neural networks. In addition, we have begun the utilization of Long-Short-Term Memory (LSTM) neural networks to allow for in-context detection of gestures with accuracy nearing 97%.
9.AD-VO: Scale-Resilient Visual Odometry Using Attentive Disparity Map ⬇️
Visual odometry is an essential key for a localization module in SLAM systems. However, previous methods require tuning the system to adapt environment changes. In this paper, we propose a learning-based approach for frame-to-frame monocular visual odometry estimation. The proposed network is only learned by disparity maps for not only covering the environment changes but also solving the scale problem. Furthermore, attention block and skip-ordering scheme are introduced to achieve robust performance in various driving environment. Our network is compared with the conventional methods which use common domain such as color or optical flow. Experimental results confirm that the proposed network shows better performance than other approaches with higher and more stable results.
10.Robust Semantic Segmentation of Brain Tumor Regions from 3D MRIs ⬇️
Multimodal brain tumor segmentation challenge (BraTS) brings together researchers to improve automated methods for 3D MRI brain tumor segmentation. Tumor segmentation is one of the fundamental vision tasks necessary for diagnosis and treatment planning of the disease. Previous years winning methods were all deep-learning based, thanks to the advent of modern GPUs, which allow fast optimization of deep convolutional neural network architectures. In this work, we explore best practices of 3D semantic segmentation, including conventional encoder-decoder architecture, as well combined loss functions, in attempt to further improve the segmentation accuracy. We evaluate the method on BraTS 2019 challenge.
11.Deep Reinforcement Learning for Active Human Pose Estimation ⬇️
Most 3d human pose estimation methods assume that input -- be it images of a scene collected from one or several viewpoints, or from a video -- is given. Consequently, they focus on estimates leveraging prior knowledge and measurement by fusing information spatially and/or temporally, whenever available. In this paper we address the problem of an active observer with freedom to move and explore the scene spatially -- in `time-freeze' mode -- and/or temporally, by selecting informative viewpoints that improve its estimation accuracy. Towards this end, we introduce Pose-DRL, a fully trainable deep reinforcement learning-based active pose estimation architecture which learns to select appropriate views, in space and time, to feed an underlying monocular pose estimator. We evaluate our model using single- and multi-target estimators with strong result in both settings. Our system further learns automatic stopping conditions in time and transition functions to the next temporal processing step in videos. In extensive experiments with the Panoptic multi-view setup, and for complex scenes containing multiple people, we show that our model learns to select viewpoints that yield significantly more accurate pose estimates compared to strong multi-view baselines.
12.Delineating Bone Surfaces in B-Mode Images Constrained by Physics of Ultrasound Propagation ⬇️
Bone surface delineation in ultrasound is of interest due to its potential in diagnosis, surgical planning, and post-operative follow-up in orthopedics, as well as the potential of using bones as anatomical landmarks in surgical navigation. We herein propose a method to encode the physics of ultrasound propagation into a factor graph formulation for the purpose of bone surface delineation. In this graph structure, unary node potentials encode the local likelihood for being a soft tissue or acoustic-shadow (behind bone surface) region, both learned through image descriptors. Pair-wise edge potentials encode ultrasound propagation constraints of bone surfaces given their large acoustic-impedance difference. We evaluate the proposed method in comparison with four earlier approaches, on in-vivo ultrasound images collected from dorsal and volar views of the forearm. The proposed method achieves an average root-mean-square error and symmetric Hausdorff distance of 0.28mm and 1.78mm, respectively. It detects 99.9% of the annotated bone surfaces with a mean scanline error (distance to annotations) of 0.39mm.
13.Detection of Diabetic Anomalies in Retinal Images using Morphological Cascading Decision Tree ⬇️
This research aims to develop an efficient system for screening of diabetic retinopathy. Diabetic retinopathy is the major cause of blindness. Severity of diabetic retinopathy is recognized by some features, such as blood vessel area, exudates, haemorrhages and microaneurysms. To grade the disease the screening system must efficiently detect these features. In this paper we are proposing a simple and fast method for detection of diabetic retinopathy. We do pre-processing of grey-scale image and find all labelled connected components (blobs) in an image regardless of whether it is haemorrhages, exudates, vessels, optic disc or anything else. Then we apply some constraints such as compactness, area of blob, intensity and contrast for screening of candidate connectedcomponent responsible for diabetic retinopathy. We obtain our final results by doing some post processing. The results are compared with ground truths. Performance is measured by finding the recall (sensitivity). We took 10 images of dimension 500 * 752. The mean recall is 90.03%.
14.A water-obstacle separation and refinement network for unmanned surface vehicles ⬇️
Obstacle detection by semantic segmentation shows a great promise for autonomous navigation in unmanned surface vehicles (USV). However, existing methods suffer from poor estimation of the water edge in the presence of visual ambiguities, poor detection of small obstacles and high false-positive rate on water reflections and wakes. We propose a new deep encoder-decoder architecture, a water-obstacle separation and refinement network (WaSR), to address these issues. Detection and water edge accuracy are improved by a novel decoder that gradually fuses inertial information from IMU with the visual features from the encoder. In addition, a novel loss function is designed to increase the separation between water and obstacle features early on in the network. Subsequently, the capacity of the remaining layers in the decoder is better utilised, leading to a significant reduction in false positives and increased true positives. Experimental results show that WaSR outperforms the current state-of-the-art by a large margin, yielding a 14% increase in F-measure over the second-best method.
15.Automated Pavement Crack Segmentation Using Fully Convolutional U-Net with a Pretrained ResNet-34 Encoder ⬇️
Automated pavement crack segmentation is a challenging task because of inherent irregular patterns and lighting conditions, in addition to the presence of noise in images. Conventional approaches require a substantial amount of feature engineering to differentiate crack regions from non-affected regions. In this paper, we propose a deep learning technique based on a convolutional neural network to perform segmentation tasks on pavement crack images. Our approach requires minimal feature engineering compared to other machine learning techniques. The proposed neural network architecture is a modified U-Net in which the encoder is replaced with a pretrained ResNet-34 network. To minimize the dice coefficient loss function, we optimize the parameters in the neural network by using an adaptive moment optimizer called AdamW. Additionally, we use a systematic method to find the optimum learning rate instead of doing parametric sweeps. We used a "one-cycle" training schedule based on cyclical learning rates to speed up the convergence. We evaluated the performance of our convolutional neural network on CFD, a pavement crack image dataset. Our method achieved an F1 score of about 96%. This is the best performance among all other algorithms tested on this dataset, outperforming the previous best method by a 1.7% margin.
16.Fast and robust multiplane single molecule localization microscopy using deep neural network ⬇️
Single molecule localization microscopy is widely used in biological research for measuring the nanostructures of samples smaller than the diffraction limit. This study uses multifocal plane microscopy and addresses the 3D single molecule localization problem, where lateral and axial locations of molecules are estimated. However, when we multifocal plane microscopy is used, the estimation accuracy of 3D localization is easily deteriorated by the small lateral drifts of camera positions. We formulate a 3D molecule localization problem along with the estimation of the lateral drifts as a compressed sensing problem, A deep neural network was applied to accurately and efficiently solve this problem. The proposed method is robust to the lateral drifts and achieves an accuracy of 20 nm laterally and 50 nm axially without an explicit drift correction.
17.From Open Set to Closed Set: Supervised Spatial Divide-and-Conquer for Object Counting ⬇️
Visual counting, a task that aims to estimate the number of objects from an image/video, is an open-set problem by nature, i.e., the number of population can vary in [0, inf) in theory. However, collected data and labeled instances are limited in reality, which means that only a small closed set is observed. Existing methods typically model this task in a regression manner, while they are prone to suffer from an unseen scene with counts out of the scope of the closed set. In fact, counting has an interesting and exclusive property---spatially decomposable. A dense region can always be divided until sub-region counts are within the previously observed closed set. We therefore introduce the idea of spatial divide-and-conquer (S-DC) that transforms open-set counting into a closed-set problem. This idea is implemented by a novel Supervised Spatial Divide-and-Conquer Network (SS-DCNet). Thus, SS-DCNet can only learn from a closed set but generalize well to open-set scenarios via S-DC. SS-DCNet is also efficient. To avoid repeatedly computing sub-region convolutional features, S-DC is executed on the feature map instead of on the input image. We provide theoretical analyses as well as a controlled experiment on toy data, demonstrating why closed-set modeling makes sense. Extensive experiments show that SS-DCNet achieves the state-of-the-art performance. Code and models are available at: this https URL.
18.MW-GAN: Multi-Warping GAN for Caricature Generation with Multi-Style Geometric Exaggeration ⬇️
Given an input face photo, the goal of caricature generation is to produce stylized, exaggerated caricatures that share the same identity as the photo. It requires simultaneous style transfer and shape exaggeration with rich diversity, and meanwhile preserving the identity of the input. To address this challenging problem, we propose a novel framework called Multi-Warping GAN (MW-GAN), including a style network and a geometric network that are designed to conduct style transfer and geometric exaggeration respectively. We bridge the gap between the style and landmarks of an image with corresponding latent code spaces by a dual way design, so as to generate caricatures with arbitrary styles and geometric exaggeration, which can be specified either through random sampling of latent code or from a given caricature sample. Besides, we apply identity preserving loss to both image space and landmark space, leading to a great improvement in quality of generated caricatures. Experiments show that caricatures generated by MW-GAN have better quality than existing methods.
19.HybridPose: 6D Object Pose Estimation under Hybrid Representations ⬇️
We introduce HybridPose, a novel 6D object pose estimation approach. HybridPose utilizes a hybrid intermediate representation to express different geometric information in the input image, including keypoints, edge vectors, and symmetry correspondences. Compared to a unitary representation, our hybrid representation allows pose regression to exploit more and diverse features when one type of predicted representation is inaccurate (e.g., because of occlusion). HybridPose leverages a robust regression module to filter out outliers in predicted intermediate representation. We show the robustness of HybridPose by demonstrating that all intermediate representations can be predicted by the same simple neural network without sacrificing the overall performance. Compared to state-of-the-art pose estimation approaches, HybridPose is comparable in running time and is significantly more accurate. For example, on Occlusion Linemod dataset, our method achieves a prediction speed of 30 fps with a mean ADD(-S) accuracy of 79.2%, representing a 67.4% improvement from the current state-of-the-art approach. Our implementation of HybridPose is available at this https URL.
20.Regression and Learning with Pixel-wise Attention for Retinal Fundus Glaucoma Segmentation and Detection ⬇️
Observing retinal fundus images by an ophthalmologist is a major diagnosis approach for glaucoma. However, it is still difficult to distinguish the features of the lesion solely through manual observations, especially, in glaucoma early phase. In this paper, we present two deep learning-based automated algorithms for glaucoma detection and optic disc and cup segmentation. We utilize the attention mechanism to learn pixel-wise features for accurate prediction. In particular, we present two convolutional neural networks that can focus on learning various pixel-wise level features. In addition, we develop several attention strategies to guide the networks to learn the important features that have a major impact on prediction accuracy. We evaluate our methods on the validation dataset and The proposed both tasks' solutions can achieve impressive results and outperform current state-of-the-art methods. \textit{The code is available at \url{this https URL}}.
21.Implementation of the VBM3D Video Denoising Method and Some Variants ⬇️
VBM3D is an extension to video of the well known image denoising algorithm BM3D, which takes advantage of the sparse representation of stacks of similar patches in a transform domain. The extension is rather straightforward: the similar 2D patches are taken from a spatio-temporal neighborhood which includes neighboring frames. In spite of its simplicity, the algorithm offers a good trade-off between denoising performance and computational complexity. In this work we revisit this method, providing an open-source C++ implementation reproducing the results. A detailed description is given and the choice of parameters is thoroughly discussed. Furthermore, we discuss several extensions of the original algorithm: (1) a multi-scale implementation, (2) the use of 3D patches, (3) the use of optical flow to guide the patch search. These extensions allow to obtain results which are competitive with even the most recent state of the art.
22.MCMLSD: A Probabilistic Algorithm and Evaluation Framework for Line Segment Detection ⬇️
Traditional approaches to line segment detection typically involve perceptual grouping in the image domain and/or global accumulation in the Hough domain. Here we propose a probabilistic algorithm that merges the advantages of both approaches. In a first stage lines are detected using a global probabilistic Hough approach. In the second stage each detected line is analyzed in the image domain to localize the line segments that generated the peak in the Hough map. By limiting search to a line, the distribution of segments over the sequence of points on the line can be modeled as a Markov chain, and a probabilistically optimal labelling can be computed exactly using a standard dynamic programming algorithm, in linear time. The Markov assumption also leads to an intuitive ranking method that uses the local marginal posterior probabilities to estimate the expected number of correctly labelled points on a segment. To assess the resulting Markov Chain Marginal Line Segment Detector (MCMLSD) we develop and apply a novel quantitative evaluation methodology that controls for under- and over-segmentation. Evaluation on the YorkUrbanDB and Wireframe datasets shows that the proposed MCMLSD method outperforms prior traditional approaches, as well as more recent deep learning methods.
23.Plug-and-Play Rescaling Based Crowd Counting in Static Images ⬇️
Crowd counting is a challenging problem especially in the presence of huge crowd diversity across images and complex cluttered crowd-like background regions, where most previous approaches do not generalize well and consequently produce either huge crowd underestimation or overestimation. To address these challenges, we propose a new image patch rescaling module (PRM) and three independent PRM employed crowd counting methods. The proposed frameworks use the PRM module to rescale the image regions (patches) that require special treatment, whereas the classification process helps in recognizing and discarding any cluttered crowd-like background regions which may result in overestimation. Experiments on three standard benchmarks and cross-dataset evaluation show that our approach outperforms the state-of-the-art models in the RMSE evaluation metric with an improvement up to 10.4%, and possesses superior generalization ability to new datasets.
24.Meshlet Priors for 3D Mesh Reconstruction ⬇️
Estimating a mesh from an unordered set of sparse, noisy 3D points is a challenging problem that requires carefully selected priors. Existing hand-crafted priors, such as smoothness regularizers, impose an undesirable trade-off between attenuating noise and preserving local detail. Recent deep-learning approaches produce impressive results by learning priors directly from the data. However, the priors are learned at the object level, which makes these algorithms class-specific, and even sensitive to the pose of the object. We introduce meshlets, small patches of mesh that we use to learn local shape priors. Meshlets act as a dictionary of local features and thus allow to use learned priors to reconstruct object meshes in any pose and from unseen classes, even when the noise is large and the samples sparse.