February 1, 2020

3218 words 16 mins read

Paper Group AWR 358

AntisymmetricRNN: A Dynamical System View on Recurrent Neural Networks. VarNet: Variational Neural Networks for the Solution of Partial Differential Equations. Safe Coordination of Human-Robot Firefighting Teams. 360SD-Net: 360° Stereo Depth Estimation with Learnable Cost Volume. Full-Stack Filters to Build Minimum Viable CNNs. Generating Timelines …

AntisymmetricRNN: A Dynamical System View on Recurrent Neural Networks


Title	AntisymmetricRNN: A Dynamical System View on Recurrent Neural Networks
Authors	Bo Chang, Minmin Chen, Eldad Haber, Ed H. Chi
Abstract	Recurrent neural networks have gained widespread use in modeling sequential data. Learning long-term dependencies using these models remains difficult though, due to exploding or vanishing gradients. In this paper, we draw connections between recurrent networks and ordinary differential equations. A special form of recurrent networks called the AntisymmetricRNN is proposed under this theoretical framework, which is able to capture long-term dependencies thanks to the stability property of its underlying differential equation. Existing approaches to improving RNN trainability often incur significant computation overhead. In comparison, AntisymmetricRNN achieves the same goal by design. We showcase the advantage of this new architecture through extensive simulations and experiments. AntisymmetricRNN exhibits much more predictable dynamics. It outperforms regular LSTM models on tasks requiring long-term memory and matches the performance on tasks where short-term dependencies dominate despite being much simpler.
Tasks
Published	2019-02-26
URL	http://arxiv.org/abs/1902.09689v1
PDF	http://arxiv.org/pdf/1902.09689v1.pdf
PWC	https://paperswithcode.com/paper/antisymmetricrnn-a-dynamical-system-view-on
Repo	https://github.com/KurochkinAlexey/AntisymmetricRNN
Framework	pytorch

VarNet: Variational Neural Networks for the Solution of Partial Differential Equations


Title	VarNet: Variational Neural Networks for the Solution of Partial Differential Equations
Authors	Reza Khodayi-Mehr, Michael M. Zavlanos
Abstract	In this paper we propose a new model-based unsupervised learning method, called VarNet, for the solution of partial differential equations (PDEs) using deep neural networks (NNs). Particularly, we propose a novel loss function that relies on the variational (integral) form of PDEs as apposed to their differential form which is commonly used in the literature. Our loss function is discretization-free, highly parallelizable, and more effective in capturing the solution of PDEs since it employs lower-order derivatives and trains over measure non-zero regions of space-time. Given this loss function, we also propose an approach to optimally select the space-time samples, used to train the NN, that is based on the feedback provided from the PDE residual. The models obtained using VarNet are smooth and do not require interpolation. They are also easily differentiable and can directly be used for control and optimization of PDEs. Finally, VarNet can straight-forwardly incorporate parametric PDE models making it a natural tool for model order reduction (MOR) of PDEs. We demonstrate the performance of our method through extensive numerical experiments for the advection-diffusion PDE as an important case-study.
Tasks
Published	2019-12-16
URL	https://arxiv.org/abs/1912.07443v1
PDF	https://arxiv.org/pdf/1912.07443v1.pdf
PWC	https://paperswithcode.com/paper/varnet-variational-neural-networks-for-the
Repo	https://github.com/RizaXudayi/VarNet
Framework	tf

Safe Coordination of Human-Robot Firefighting Teams


Title	Safe Coordination of Human-Robot Firefighting Teams
Authors	Esmaeil Seraj, Andrew Silva, Matthew Gombolay
Abstract	Wildfires are destructive and inflict massive, irreversible harm to victims’ lives and natural resources. Researchers have proposed commissioning unmanned aerial vehicles (UAVs) to provide firefighters with real-time tracking information; yet, these UAVs are not able to reason about a fire’s track, including current location, measurement, and uncertainty, as well as propagation. We propose a model-predictive, probabilistically safe distributed control algorithm for human-robot collaboration in wildfire fighting. The proposed algorithm overcomes the limitations of prior work by explicitly estimating the latent fire propagation dynamics to enable intelligent, time-extended coordination of the UAVs in support of on-the-ground human firefighters. We derive a novel, analytical bound that enables UAVs to distribute their resources and provides a probabilistic guarantee of the humans’ safety while preserving the UAVs’ ability to cover an entire fire.
Tasks
Published	2019-03-16
URL	http://arxiv.org/abs/1903.06847v1
PDF	http://arxiv.org/pdf/1903.06847v1.pdf
PWC	https://paperswithcode.com/paper/safe-coordination-of-human-robot-firefighting
Repo	https://github.com/firefront-tracking/Safe-Coordination-of-Human-Robot-Firefighting-Teams
Framework	none

360SD-Net: 360° Stereo Depth Estimation with Learnable Cost Volume


Title	360SD-Net: 360° Stereo Depth Estimation with Learnable Cost Volume
Authors	Ning-Hsu Wang, Bolivar Solarte, Yi-Hsuan Tsai, Wei-Chen Chiu, Min Sun
Abstract	Recently, end-to-end trainable deep neural networks have significantly improved stereo depth estimation for perspective images. However, 360{\deg} images captured under equirectangular projection cannot benefit from directly adopting existing methods due to distortion introduced (i.e., lines in 3D are not projected onto lines in 2D). To tackle this issue, we present a novel architecture specifically designed for spherical disparity using the setting of top-bottom 360{\deg} camera pairs. Moreover, we propose to mitigate the distortion issue by (1) an additional input branch capturing the position and relation of each pixel in the spherical coordinate, and (2) a cost volume built upon a learnable shifting filter. Due to the lack of 360{\deg} stereo data, we collect two 360{\deg} stereo datasets from Matterport3D and Stanford3D for training and evaluation. Extensive experiments and ablation study are provided to validate our method against existing algorithms. Finally, we show promising results on real-world environments capturing images with two consumer-level cameras.
Tasks	Depth Estimation, Stereo Depth Estimation
Published	2019-11-11
URL	https://arxiv.org/abs/1911.04460v2
PDF	https://arxiv.org/pdf/1911.04460v2.pdf
PWC	https://paperswithcode.com/paper/360sd-net-360-stereo-depth-estimation-with
Repo	https://github.com/albert100121/360SD-Net
Framework	pytorch

Full-Stack Filters to Build Minimum Viable CNNs


Title	Full-Stack Filters to Build Minimum Viable CNNs
Authors	Kai Han, Yunhe Wang, Yixing Xu, Chunjing Xu, Dacheng Tao, Chang Xu
Abstract	Deep convolutional neural networks (CNNs) are usually over-parameterized, which cannot be easily deployed on edge devices such as mobile phones and smart cameras. Existing works used to decrease the number or size of requested convolution filters for a minimum viable CNN on edge devices. In contrast, this paper introduces filters that are full-stack and can be used to generate many more sub-filters. Weights of these sub-filters are inherited from full-stack filters with the help of different binary masks. Orthogonal constraints are applied over binary masks to decrease their correlation and promote the diversity of generated sub-filters. To preserve the same volume of output feature maps, we can naturally reduce the number of established filters by only maintaining a few full-stack filters and a set of binary masks. We also conduct theoretical analysis on the memory cost and an efficient implementation is introduced for the convolution of the proposed filters. Experiments on several benchmark datasets and CNN models demonstrate that the proposed method is able to construct minimum viable convolution networks of comparable performance.
Tasks
Published	2019-08-06
URL	https://arxiv.org/abs/1908.02023v1
PDF	https://arxiv.org/pdf/1908.02023v1.pdf
PWC	https://paperswithcode.com/paper/full-stack-filters-to-build-minimum-viable
Repo	https://github.com/huawei-noah/Full-Stack-Filters
Framework	pytorch

Generating Timelines by Modeling Semantic Change


Title	Generating Timelines by Modeling Semantic Change
Authors	Guy D. Rosin, Kira Radinsky
Abstract	Though languages can evolve slowly, they can also react strongly to dramatic world events. By studying the connection between words and events, it is possible to identify which events change our vocabulary and in what way. In this work, we tackle the task of creating timelines - records of historical “turning points”, represented by either words or events, to understand the dynamics of a target word. Our approach identifies these points by leveraging both static and time-varying word embeddings to measure the influence of words and events. In addition to quantifying changes, we show how our technique can help isolate semantic changes. Our qualitative and quantitative evaluations show that we are able to capture this semantic change and event influence.
Tasks	Word Embeddings
Published	2019-09-21
URL	https://arxiv.org/abs/1909.09907v1
PDF	https://arxiv.org/pdf/1909.09907v1.pdf
PWC	https://paperswithcode.com/paper/190909907
Repo	https://github.com/guyrosin/generating_timelines
Framework	none

Deep Plug-and-Play Super-Resolution for Arbitrary Blur Kernels


Title	Deep Plug-and-Play Super-Resolution for Arbitrary Blur Kernels
Authors	Kai Zhang, Wangmeng Zuo, Lei Zhang
Abstract	While deep neural networks (DNN) based single image super-resolution (SISR) methods are rapidly gaining popularity, they are mainly designed for the widely-used bicubic degradation, and there still remains the fundamental challenge for them to super-resolve low-resolution (LR) image with arbitrary blur kernels. In the meanwhile, plug-and-play image restoration has been recognized with high flexibility due to its modular structure for easy plug-in of denoiser priors. In this paper, we propose a principled formulation and framework by extending bicubic degradation based deep SISR with the help of plug-and-play framework to handle LR images with arbitrary blur kernels. Specifically, we design a new SISR degradation model so as to take advantage of existing blind deblurring methods for blur kernel estimation. To optimize the new degradation induced energy function, we then derive a plug-and-play algorithm via variable splitting technique, which allows us to plug any super-resolver prior rather than the denoiser prior as a modular part. Quantitative and qualitative evaluations on synthetic and real LR images demonstrate that the proposed deep plug-and-play super-resolution framework is flexible and effective to deal with blurry LR images.
Tasks	Deblurring, Image Restoration, Image Super-Resolution, Super-Resolution
Published	2019-03-29
URL	http://arxiv.org/abs/1903.12529v1
PDF	http://arxiv.org/pdf/1903.12529v1.pdf
PWC	https://paperswithcode.com/paper/deep-plug-and-play-super-resolution-for
Repo	https://github.com/cszn/DPSR
Framework	pytorch

Diversify Your Datasets: Analyzing Generalization via Controlled Variance in Adversarial Datasets


Title	Diversify Your Datasets: Analyzing Generalization via Controlled Variance in Adversarial Datasets
Authors	Ohad Rozen, Vered Shwartz, Roee Aharoni, Ido Dagan
Abstract	Phenomenon-specific “adversarial” datasets have been recently designed to perform targeted stress-tests for particular inference types. Recent work (Liu et al., 2019a) proposed that such datasets can be utilized for training NLI and other types of models, often allowing to learn the phenomenon in focus and improve on the challenge dataset, indicating a “blind spot” in the original training data. Yet, although a model can improve in such a training process, it might still be vulnerable to other challenge datasets targeting the same phenomenon but drawn from a different distribution, such as having a different syntactic complexity level. In this work, we extend this method to drive conclusions about a model’s ability to learn and generalize a target phenomenon rather than to “learn” a dataset, by controlling additional aspects in the adversarial datasets. We demonstrate our approach on two inference phenomena - dative alternation and numerical reasoning, elaborating, and in some cases contradicting, the results of Liu et al.. Our methodology enables building better challenge datasets for creating more robust models, and may yield better model understanding and subsequent overarching improvements.
Tasks
Published	2019-10-21
URL	https://arxiv.org/abs/1910.09302v1
PDF	https://arxiv.org/pdf/1910.09302v1.pdf
PWC	https://paperswithcode.com/paper/diversify-your-datasets-analyzing
Repo	https://github.com/ohadrozen/generalization
Framework	none

Concept Pointer Network for Abstractive Summarization


Title	Concept Pointer Network for Abstractive Summarization
Authors	Wang Wenbo, Gao Yang, Huang Heyan, Zhou Yuxiang
Abstract	A quality abstractive summary should not only copy salient source texts as summaries but should also tend to generate new conceptual words to express concrete details. Inspired by the popular pointer generator sequence-to-sequence model, this paper presents a concept pointer network for improving these aspects of abstractive summarization. The network leverages knowledge-based, context-aware conceptualizations to derive an extended set of candidate concepts. The model then points to the most appropriate choice using both the concept set and original source text. This joint approach generates abstractive summaries with higher-level semantic concepts. The training model is also optimized in a way that adapts to different data, which is based on a novel method of distantly-supervised learning guided by reference summaries and testing set. Overall, the proposed approach provides statistically significant improvements over several state-of-the-art models on both the DUC-2004 and Gigaword datasets. A human evaluation of the model’s abstractive abilities also supports the quality of the summaries produced within this framework.
Tasks	Abstractive Text Summarization, Text Summarization
Published	2019-10-18
URL	https://arxiv.org/abs/1910.08486v1
PDF	https://arxiv.org/pdf/1910.08486v1.pdf
PWC	https://paperswithcode.com/paper/concept-pointer-network-for-abstractive
Repo	https://github.com/wprojectsn/codes
Framework	pytorch

Meta Reinforcement Learning with Task Embedding and Shared Policy


Title	Meta Reinforcement Learning with Task Embedding and Shared Policy
Authors	Lin Lan, Zhenguo Li, Xiaohong Guan, Pinghui Wang
Abstract	Despite significant progress, deep reinforcement learning (RL) suffers from data-inefficiency and limited generalization. Recent efforts apply meta-learning to learn a meta-learner from a set of RL tasks such that a novel but related task could be solved quickly. Though specific in some ways, different tasks in meta-RL are generally similar at a high level. However, most meta-RL methods do not explicitly and adequately model the specific and shared information among different tasks, which limits their ability to learn training tasks and to generalize to novel tasks. In this paper, we propose to capture the shared information on the one hand and meta-learn how to quickly abstract the specific information about a task on the other hand. Methodologically, we train an SGD meta-learner to quickly optimize a task encoder for each task, which generates a task embedding based on past experience. Meanwhile, we learn a policy which is shared across all tasks and conditioned on task embeddings. Empirical results on four simulated tasks demonstrate that our method has better learning capacity on both training and novel tasks and attains up to 3 to 4 times higher returns compared to baselines.
Tasks	Meta-Learning
Published	2019-05-16
URL	https://arxiv.org/abs/1905.06527v3
PDF	https://arxiv.org/pdf/1905.06527v3.pdf
PWC	https://paperswithcode.com/paper/meta-reinforcement-learning-with-task
Repo	https://github.com/llan-ml/tesp
Framework	tf

Towards Stable and Efficient Training of Verifiably Robust Neural Networks


Title	Towards Stable and Efficient Training of Verifiably Robust Neural Networks
Authors	Huan Zhang, Hongge Chen, Chaowei Xiao, Sven Gowal, Robert Stanforth, Bo Li, Duane Boning, Cho-Jui Hsieh
Abstract	Training neural networks with verifiable robustness guarantees is challenging. Several existing approaches utilize linear relaxation based neural network output bounds under perturbation, but they can slow down training by a factor of hundreds depending on the underlying network architectures. Meanwhile, interval bound propagation (IBP) based training is efficient and significantly outperforms linear relaxation based methods on many tasks, yet it may suffer from stability issues since the bounds are much looser especially at the beginning of training. In this paper, we propose a new certified adversarial training method, CROWN-IBP, by combining the fast IBP bounds in a forward bounding pass and a tight linear relaxation based bound, CROWN, in a backward bounding pass. CROWN-IBP is computationally efficient and consistently outperforms IBP baselines on training verifiably robust neural networks. We conduct large scale experiments on MNIST and CIFAR datasets, and outperform all previous linear relaxation and bound propagation based certified defenses in $\ell_\infty$ robustness. Notably, we achieve 7.02% verified test error on MNIST at $\epsilon=0.3$, and 66.94% on CIFAR-10 with $\epsilon=8/255$. Code is available at https://github.com/deepmind/interval-bound-propagation (TensorFlow) and https://github.com/huanzhang12/CROWN-IBP (PyTorch).
Tasks
Published	2019-06-14
URL	https://arxiv.org/abs/1906.06316v2
PDF	https://arxiv.org/pdf/1906.06316v2.pdf
PWC	https://paperswithcode.com/paper/towards-stable-and-efficient-training-of
Repo	https://github.com/KaidiXu/auto_LiRPA
Framework	pytorch

A Baseline for 3D Multi-Object Tracking


Title	A Baseline for 3D Multi-Object Tracking
Authors	Xinshuo Weng, Kris Kitani
Abstract	3D multi-object tracking (MOT) is an essential component technology for many real-time applications such as autonomous driving or assistive robotics. Recent work on 3D MOT tend to focus more on developing accurate systems giving less regard to computational cost and system complexity. In contrast, this work proposes a simple yet accurate real-time 3D MOT system. We use an off-the-shelf 3D object detector to obtain oriented 3D bounding boxes from the LiDAR point cloud. Then, a combination of 3D Kalman filter and Hungarian algorithm is used for state estimation and data association. Although our baseline system is a straightforward combination of standard methods, we obtain the state-of-the-art results. To evaluate our baseline system, we propose a new 3D MOT extension to the official KITTI 2D MOT evaluation along with a set of new metrics. Our proposed baseline method for 3D MOT establishes new state-of-the-art performance on 3D MOT for KITTI. Surprisingly, although our baseline system does not use any 2D data as input, we place 2nd on the official KITTI 2D MOT leaderboard. Also, our proposed 3D MOT method runs at a rate of $214.7$ FPS, achieving the fastest speed among all modern MOT systems. Our code is publicly available at https://github.com/xinshuoweng/AB3DMOT
Tasks	3D Multi-Object Tracking, Autonomous Driving, Multi-Object Tracking, Object Tracking
Published	2019-07-09
URL	https://arxiv.org/abs/1907.03961v3
PDF	https://arxiv.org/pdf/1907.03961v3.pdf
PWC	https://paperswithcode.com/paper/a-baseline-for-3d-multi-object-tracking
Repo	https://github.com/xinshuoweng/AB3DMOT
Framework	none

Pothole Detection Based on Disparity Transformation and Road Surface Modeling


Title	Pothole Detection Based on Disparity Transformation and Road Surface Modeling
Authors	Rui Fan, Umar Ozgunalp, Brett Hosking, Ming Liu, Ioannis Pitas
Abstract	Pothole detection is one of the most important tasks for road maintenance. Computer vision approaches are generally based on either 2D road image analysis or 3D road surface modeling. However, these two categories are always used independently. Furthermore, the pothole detection accuracy is still far from satisfactory. Therefore, in this paper, we present a robust pothole detection algorithm that is both accurate and computationally efficient. A dense disparity map is first transformed to better distinguish between damaged and undamaged road areas. To achieve greater disparity transformation efficiency, golden section search and dynamic programming are utilized to estimate the transformation parameters. Otsu’s thresholding method is then used to extract potential undamaged road areas from the transformed disparity map. The disparities in the extracted areas are modeled by a quadratic surface using least squares fitting. To improve disparity map modeling robustness, the surface normal is also integrated into the surface modeling process. Furthermore, random sample consensus is utilized to reduce the effects caused by outliers. By comparing the difference between the actual and modeled disparity maps, the potholes can be detected accurately. Finally, the point clouds of the detected potholes are extracted from the reconstructed 3D road surface. The experimental results show that the successful detection accuracy of the proposed system is around 98.7% and the overall pixel-level accuracy is approximately 99.6%.
Tasks
Published	2019-08-02
URL	https://arxiv.org/abs/1908.00894v2
PDF	https://arxiv.org/pdf/1908.00894v2.pdf
PWC	https://paperswithcode.com/paper/pothole-detection-based-on-disparity
Repo	https://github.com/ruirangerfan/stereo_pothole_datasets
Framework	none

Weakly Supervised Cell Instance Segmentation by Propagating from Detection Response


Title	Weakly Supervised Cell Instance Segmentation by Propagating from Detection Response
Authors	Kazuya Nishimura, Dai Fei Elmer Ker, Ryoma Bise
Abstract	Cell shape analysis is important in biomedical research. Deep learning methods may perform to segment individual cells if they use sufficient training data that the boundary of each cell is annotated. However, it is very time-consuming for preparing such detailed annotation for many cell culture conditions. In this paper, we propose a weakly supervised method that can segment individual cell regions who touch each other with unclear boundaries in dense conditions without the training data for cell regions. We demonstrated the efficacy of our method using several data-set including multiple cell types captured by several types of microscopy. Our method achieved the highest accuracy compared with several conventional methods. In addition, we demonstrated that our method can perform without any annotation by using fluorescence images that cell nuclear were stained as training data. Code is publicly available in “https://github.com/naivete5656/WSISPDR".
Tasks	Instance Segmentation, Semantic Segmentation
Published	2019-11-29
URL	https://arxiv.org/abs/1911.13077v1
PDF	https://arxiv.org/pdf/1911.13077v1.pdf
PWC	https://paperswithcode.com/paper/weakly-supervised-cell-instance-segmentation
Repo	https://github.com/naivete5656/WSISPDR
Framework	pytorch

Testing for Association in Multi-View Network Data


Title	Testing for Association in Multi-View Network Data
Authors	Lucy L. Gao, Daniela Witten, Jacob Bien
Abstract	In this paper, we consider data consisting of multiple networks, each comprised of a different edge set on a common set of nodes. Many models have been proposed for the analysis of such multi-view network data under the assumption that the data views are closely related. In this paper, we provide tools for evaluating this assumption. In particular, we ask: given two networks that each follow a stochastic block model, is there an association between the latent community memberships of the nodes in the two networks? To answer this question, we extend the stochastic block model for a single network view to the two-view setting, and develop a new hypothesis test for the null hypothesis that the latent community memberships in the two data views are independent. We apply our test to protein-protein interaction data from the HINT database (Das and Hint, 2012). We find evidence of a weak association between the latent community memberships of proteins defined with respect to binary interaction data and the latent community memberships of proteins defined with respect to co-complex association data. We also extend this proposal to the setting of a network with node covariates.
Tasks
Published	2019-09-25
URL	https://arxiv.org/abs/1909.11640v2
PDF	https://arxiv.org/pdf/1909.11640v2.pdf
PWC	https://paperswithcode.com/paper/testing-for-association-in-multi-view-network
Repo	https://github.com/lucylgao/mv-network-test-code
Framework	none