October 21, 2019

3144 words 15 mins read

Paper Group AWR 47

Structured Variational Learning of Bayesian Neural Networks with Horseshoe Priors. Weakly Supervised Object Detection in Artworks. Certified Adversarial Robustness with Additive Noise. CubeSLAM: Monocular 3D Object SLAM. Unsupervised Alignment of Embeddings with Wasserstein Procrustes. Perfect Match: A Simple Method for Learning Representations For …

Structured Variational Learning of Bayesian Neural Networks with Horseshoe Priors


Title	Structured Variational Learning of Bayesian Neural Networks with Horseshoe Priors
Authors	Soumya Ghosh, Jiayu Yao, Finale Doshi-Velez
Abstract	Bayesian Neural Networks (BNNs) have recently received increasing attention for their ability to provide well-calibrated posterior uncertainties. However, model selection—even choosing the number of nodes—remains an open question. Recent work has proposed the use of a horseshoe prior over node pre-activations of a Bayesian neural network, which effectively turns off nodes that do not help explain the data. In this work, we propose several modeling and inference advances that consistently improve the compactness of the model learned while maintaining predictive performance, especially in smaller-sample settings including reinforcement learning.
Tasks	Model Selection
Published	2018-06-13
URL	http://arxiv.org/abs/1806.05975v2
PDF	http://arxiv.org/pdf/1806.05975v2.pdf
PWC	https://paperswithcode.com/paper/structured-variational-learning-of-bayesian
Repo	https://github.com/hughsalimbeni/bayesian_benchmarks
Framework	none

Weakly Supervised Object Detection in Artworks


Title	Weakly Supervised Object Detection in Artworks
Authors	Nicolas Gonthier, Yann Gousseau, Said Ladjal, Olivier Bonfait
Abstract	We propose a method for the weakly supervised detection of objects in paintings. At training time, only image-level annotations are needed. This, combined with the efficiency of our multiple-instance learning method, enables one to learn new classes on-the-fly from globally annotated databases, avoiding the tedious task of manually marking objects. We show on several databases that dropping the instance-level annotations only yields mild performance losses. We also introduce a new database, IconArt, on which we perform detection experiments on classes that could not be learned on photographs, such as Jesus Child or Saint Sebastian. To the best of our knowledge, these are the first experiments dealing with the automatic (and in our case weakly supervised) detection of iconographic elements in paintings. We believe that such a method is of great benefit for helping art historians to explore large digital databases.
Tasks	Multiple Instance Learning, Object Detection, Weakly Supervised Object Detection
Published	2018-10-05
URL	http://arxiv.org/abs/1810.02569v1
PDF	http://arxiv.org/pdf/1810.02569v1.pdf
PWC	https://paperswithcode.com/paper/weakly-supervised-object-detection-in
Repo	https://github.com/nicaogr/Mi_max
Framework	tf

Certified Adversarial Robustness with Additive Noise


Title	Certified Adversarial Robustness with Additive Noise
Authors	Bai Li, Changyou Chen, Wenlin Wang, Lawrence Carin
Abstract	The existence of adversarial data examples has drawn significant attention in the deep-learning community; such data are seemingly minimally perturbed relative to the original data, but lead to very different outputs from a deep-learning algorithm. Although a significant body of work on developing defensive models has been considered, most such models are heuristic and are often vulnerable to adaptive attacks. Defensive methods that provide theoretical robustness guarantees have been studied intensively, yet most fail to obtain non-trivial robustness when a large-scale model and data are present. To address these limitations, we introduce a framework that is scalable and provides certified bounds on the norm of the input manipulation for constructing adversarial examples. We establish a connection between robustness against adversarial perturbation and additive random noise, and propose a training strategy that can significantly improve the certified bounds. Our evaluation on MNIST, CIFAR-10 and ImageNet suggests that the proposed method is scalable to complicated models and large data sets, while providing competitive robustness to state-of-the-art provable defense methods.
Tasks	Adversarial Attack
Published	2018-09-10
URL	https://arxiv.org/abs/1809.03113v6
PDF	https://arxiv.org/pdf/1809.03113v6.pdf
PWC	https://paperswithcode.com/paper/second-order-adversarial-attack-and
Repo	https://github.com/locuslab/smoothing
Framework	pytorch

CubeSLAM: Monocular 3D Object SLAM


Title	CubeSLAM: Monocular 3D Object SLAM
Authors	Shichao Yang, Sebastian Scherer
Abstract	We present a method for single image 3D cuboid object detection and multi-view object SLAM in both static and dynamic environments, and demonstrate that the two parts can improve each other. Firstly for single image object detection, we generate high-quality cuboid proposals from 2D bounding boxes and vanishing points sampling. The proposals are further scored and selected based on the alignment with image edges. Secondly, multi-view bundle adjustment with new object measurements is proposed to jointly optimize poses of cameras, objects and points. Objects can provide long-range geometric and scale constraints to improve camera pose estimation and reduce monocular drift. Instead of treating dynamic regions as outliers, we utilize object representation and motion model constraints to improve the camera pose estimation. The 3D detection experiments on SUN RGBD and KITTI show better accuracy and robustness over existing approaches. On the public TUM, KITTI odometry and our own collected datasets, our SLAM method achieves the state-of-the-art monocular camera pose estimation and at the same time, improves the 3D object detection accuracy.
Tasks	3D Object Detection, Object Detection, Pose Estimation
Published	2018-06-01
URL	http://arxiv.org/abs/1806.00557v2
PDF	http://arxiv.org/pdf/1806.00557v2.pdf
PWC	https://paperswithcode.com/paper/cubeslam-monocular-3d-object-detection-and
Repo	https://github.com/shichaoy/cube_slam
Framework	none

Unsupervised Alignment of Embeddings with Wasserstein Procrustes


Title	Unsupervised Alignment of Embeddings with Wasserstein Procrustes
Authors	Edouard Grave, Armand Joulin, Quentin Berthet
Abstract	A library for Multilingual Unsupervised or Supervised word Embeddings
Tasks	Word Embeddings
Published	2018-05-29
URL	http://arxiv.org/abs/1805.11222v1
PDF	http://arxiv.org/pdf/1805.11222v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-alignment-of-embeddings-with
Repo	https://github.com/facebookresearch/MUSE
Framework	pytorch

Perfect Match: A Simple Method for Learning Representations For Counterfactual Inference With Neural Networks


Title	Perfect Match: A Simple Method for Learning Representations For Counterfactual Inference With Neural Networks
Authors	Patrick Schwab, Lorenz Linhardt, Walter Karlen
Abstract	Learning representations for counterfactual inference from observational data is of high practical relevance for many domains, such as healthcare, public policy and economics. Counterfactual inference enables one to answer “What if…?” questions, such as “What would be the outcome if we gave this patient treatment $t_1$?". However, current methods for training neural networks for counterfactual inference on observational data are either overly complex, limited to settings with only two available treatments, or both. Here, we present Perfect Match (PM), a method for training neural networks for counterfactual inference that is easy to implement, compatible with any architecture, does not add computational complexity or hyperparameters, and extends to any number of treatments. PM is based on the idea of augmenting samples within a minibatch with their propensity-matched nearest neighbours. Our experiments demonstrate that PM outperforms a number of more complex state-of-the-art methods in inferring counterfactual outcomes across several benchmarks, particularly in settings with many treatments.
Tasks	Counterfactual Inference
Published	2018-10-01
URL	https://arxiv.org/abs/1810.00656v5
PDF	https://arxiv.org/pdf/1810.00656v5.pdf
PWC	https://paperswithcode.com/paper/perfect-match-a-simple-method-for-learning
Repo	https://github.com/d909b/perfect_match
Framework	none

Brain Tumor Segmentation and Radiomics Survival Prediction: Contribution to the BRATS 2017 Challenge


Title	Brain Tumor Segmentation and Radiomics Survival Prediction: Contribution to the BRATS 2017 Challenge
Authors	Fabian Isensee, Philipp Kickingereder, Wolfgang Wick, Martin Bendszus, Klaus H. Maier-Hein
Abstract	Quantitative analysis of brain tumors is critical for clinical decision making. While manual segmentation is tedious, time consuming and subjective, this task is at the same time very challenging to solve for automatic segmentation methods. In this paper we present our most recent effort on developing a robust segmentation algorithm in the form of a convolutional neural network. Our network architecture was inspired by the popular U-Net and has been carefully modified to maximize brain tumor segmentation performance. We use a dice loss function to cope with class imbalances and use extensive data augmentation to successfully prevent overfitting. Our method beats the current state of the art on BraTS 2015, is one of the leading methods on the BraTS 2017 validation set (dice scores of 0.896, 0.797 and 0.732 for whole tumor, tumor core and enhancing tumor, respectively) and achieves very good Dice scores on the test set (0.858 for whole, 0.775 for core and 0.647 for enhancing tumor). We furthermore take part in the survival prediction subchallenge by training an ensemble of a random forest regressor and multilayer perceptrons on shape features describing the tumor subregions. Our approach achieves 52.6% accuracy, a Spearman correlation coefficient of 0.496 and a mean square error of 209607 on the test set.
Tasks	Brain Tumor Segmentation, Data Augmentation, Decision Making
Published	2018-02-28
URL	http://arxiv.org/abs/1802.10508v1
PDF	http://arxiv.org/pdf/1802.10508v1.pdf
PWC	https://paperswithcode.com/paper/brain-tumor-segmentation-and-radiomics
Repo	https://github.com/pykao/Modified-3D-UNet-Pytorch
Framework	pytorch

Robustness via Retrying: Closed-Loop Robotic Manipulation with Self-Supervised Learning


Title	Robustness via Retrying: Closed-Loop Robotic Manipulation with Self-Supervised Learning
Authors	Frederik Ebert, Sudeep Dasari, Alex X. Lee, Sergey Levine, Chelsea Finn
Abstract	Prediction is an appealing objective for self-supervised learning of behavioral skills, particularly for autonomous robots. However, effectively utilizing predictive models for control, especially with raw image inputs, poses a number of major challenges. How should the predictions be used? What happens when they are inaccurate? In this paper, we tackle these questions by proposing a method for learning robotic skills from raw image observations, using only autonomously collected experience. We show that even an imperfect model can complete complex tasks if it can continuously retry, but this requires the model to not lose track of the objective (e.g., the object of interest). To enable a robot to continuously retry a task, we devise a self-supervised algorithm for learning image registration, which can keep track of objects of interest for the duration of the trial. We demonstrate that this idea can be combined with a video-prediction based controller to enable complex behaviors to be learned from scratch using only raw visual inputs, including grasping, repositioning objects, and non-prehensile manipulation. Our real-world experiments demonstrate that a model trained with 160 robot hours of autonomously collected, unlabeled data is able to successfully perform complex manipulation tasks with a wide range of objects not seen during training.
Tasks	Image Registration, Video Prediction
Published	2018-10-06
URL	http://arxiv.org/abs/1810.03043v1
PDF	http://arxiv.org/pdf/1810.03043v1.pdf
PWC	https://paperswithcode.com/paper/robustness-via-retrying-closed-loop-robotic
Repo	https://github.com/shijiwensjw/vp_based_control
Framework	none

Deconfounding Reinforcement Learning in Observational Settings


Title	Deconfounding Reinforcement Learning in Observational Settings
Authors	Chaochao Lu, Bernhard Schölkopf, José Miguel Hernández-Lobato
Abstract	We propose a general formulation for addressing reinforcement learning (RL) problems in settings with observational data. That is, we consider the problem of learning good policies solely from historical data in which unobserved factors (confounders) affect both observed actions and rewards. Our formulation allows us to extend a representative RL algorithm, the Actor-Critic method, to its deconfounding variant, with the methodology for this extension being easily applied to other RL algorithms. In addition to this, we develop a new benchmark for evaluating deconfounding RL algorithms by modifying the OpenAI Gym environments and the MNIST dataset. Using this benchmark, we demonstrate that the proposed algorithms are superior to traditional RL methods in confounded environments with observational data. To the best of our knowledge, this is the first time that confounders are taken into consideration for addressing full RL problems with observational data. Code is available at https://github.com/CausalRL/DRL.
Tasks
Published	2018-12-26
URL	http://arxiv.org/abs/1812.10576v1
PDF	http://arxiv.org/pdf/1812.10576v1.pdf
PWC	https://paperswithcode.com/paper/deconfounding-reinforcement-learning-in
Repo	https://github.com/CausalRL/DRL
Framework	tf

YouTube AV 50K: An Annotated Corpus for Comments in Autonomous Vehicles


Title	YouTube AV 50K: An Annotated Corpus for Comments in Autonomous Vehicles
Authors	Tao Li, Lei Lin, Minsoo Choi, Kaiming Fu, Siyuan Gong, Jian Wang
Abstract	With one billion monthly viewers, and millions of users discussing and sharing opinions, comments below YouTube videos are rich sources of data for opinion mining and sentiment analysis. We introduce the YouTube AV 50K dataset, a freely-available collections of more than 50,000 YouTube comments and metadata below autonomous vehicle (AV)-related videos. We describe its creation process, its content and data format, and discuss its possible usages. Especially, we do a case study of the first self-driving car fatality to evaluate the dataset, and show how we can use this dataset to better understand public attitudes toward self-driving cars and public reactions to the accident. Future developments of the dataset are also discussed.
Tasks	Autonomous Vehicles, Opinion Mining, Self-Driving Cars, Sentiment Analysis
Published	2018-07-30
URL	http://arxiv.org/abs/1807.11227v4
PDF	http://arxiv.org/pdf/1807.11227v4.pdf
PWC	https://paperswithcode.com/paper/youtube-av-50k-an-annotated-corpus-for
Repo	https://github.com/Eroica-cpp/YouTube-Statistics
Framework	none

CLAIRE: A distributed-memory solver for constrained large deformation diffeomorphic image registration


Title	CLAIRE: A distributed-memory solver for constrained large deformation diffeomorphic image registration
Authors	Andreas Mang, Amir Gholami, Christos Davatzikos, George Biros
Abstract	With this work, we release CLAIRE, a distributed-memory implementation of an effective solver for constrained large deformation diffeomorphic image registration problems in three dimensions. We consider an optimal control formulation. We invert for a stationary velocity field that parameterizes the deformation map. Our solver is based on a globalized, preconditioned, inexact reduced space Gauss–Newton–Krylov scheme. We exploit state-of-the-art techniques in scientific computing to develop an effective solver that scales to thousands of distributed memory nodes on high-end clusters. We present the formulation, discuss algorithmic features, describe the software package, and introduce an improved preconditioner for the reduced space Hessian to speed up the convergence of our solver. We test registration performance on synthetic and real data. We demonstrate registration accuracy on several neuroimaging datasets. We compare the performance of our scheme against different flavors of the Demons algorithm for diffeomorphic image registration. We study convergence of our preconditioner and our overall algorithm. We report scalability results on state-of-the-art supercomputing platforms. We demonstrate that we can solve registration problems for clinically relevant data sizes in two to four minutes on a standard compute node with 20 cores, attaining excellent data fidelity. With the present work we achieve a speedup of (on average) 5$\times$ with a peak performance of up to 17$\times$ compared to our former work.
Tasks	Image Registration
Published	2018-08-13
URL	https://arxiv.org/abs/1808.04487v2
PDF	https://arxiv.org/pdf/1808.04487v2.pdf
PWC	https://paperswithcode.com/paper/claire-a-distributed-memory-solver-for
Repo	https://github.com/andreasmang/claire
Framework	none

Multi-level Wavelet-CNN for Image Restoration


Title	Multi-level Wavelet-CNN for Image Restoration
Authors	Pengju Liu, Hongzhi Zhang, Kai Zhang, Liang Lin, Wangmeng Zuo
Abstract	The tradeoff between receptive field size and efficiency is a crucial issue in low level vision. Plain convolutional networks (CNNs) generally enlarge the receptive field at the expense of computational cost. Recently, dilated filtering has been adopted to address this issue. But it suffers from gridding effect, and the resulting receptive field is only a sparse sampling of input image with checkerboard patterns. In this paper, we present a novel multi-level wavelet CNN (MWCNN) model for better tradeoff between receptive field size and computational efficiency. With the modified U-Net architecture, wavelet transform is introduced to reduce the size of feature maps in the contracting subnetwork. Furthermore, another convolutional layer is further used to decrease the channels of feature maps. In the expanding subnetwork, inverse wavelet transform is then deployed to reconstruct the high resolution feature maps. Our MWCNN can also be explained as the generalization of dilated filtering and subsampling, and can be applied to many image restoration tasks. The experimental results clearly show the effectiveness of MWCNN for image denoising, single image super-resolution, and JPEG image artifacts removal.
Tasks	Denoising, Image Denoising, Image Restoration, Image Super-Resolution, Super-Resolution
Published	2018-05-18
URL	http://arxiv.org/abs/1805.07071v2
PDF	http://arxiv.org/pdf/1805.07071v2.pdf
PWC	https://paperswithcode.com/paper/multi-level-wavelet-cnn-for-image-restoration
Repo	https://github.com/MatusPilnan/nsiete-project
Framework	tf

Fast and Robust Symmetric Image Registration Based on Distances Combining Intensity and Spatial Information


Title	Fast and Robust Symmetric Image Registration Based on Distances Combining Intensity and Spatial Information
Authors	Johan Öfverstedt, Joakim Lindblad, Nataša Sladoje
Abstract	Intensity-based image registration approaches rely on similarity measures to guide the search for geometric correspondences with high affinity between images. The properties of the used measure are vital for the robustness and accuracy of the registration. In this study a symmetric, intensity interpolation-free, affine registration framework based on a combination of intensity and spatial information is proposed. The excellent performance of the framework is demonstrated on a combination of synthetic tests, recovering known transformations in the presence of noise, and real applications in biomedical and medical image registration, for both 2D and 3D images. The method exhibits greater robustness and higher accuracy than similarity measures in common use, when inserted into a standard gradient-based registration framework available as part of the open source Insight Segmentation and Registration Toolkit (ITK). The method is also empirically shown to have a low computational cost, making it practical for real applications. Source code is available.
Tasks	Image Registration, Medical Image Registration
Published	2018-07-30
URL	http://arxiv.org/abs/1807.11599v2
PDF	http://arxiv.org/pdf/1807.11599v2.pdf
PWC	https://paperswithcode.com/paper/fast-and-robust-symmetric-image-registration
Repo	https://github.com/MIDA-group/py_alpha_amd_release
Framework	none

Repeatability of Multiparametric Prostate MRI Radiomics Features


Title	Repeatability of Multiparametric Prostate MRI Radiomics Features
Authors	Michael Schwier, Joost van Griethuysen, Mark G Vangel, Steve Pieper, Sharon Peled, Clare M Tempany, Hugo JWL Aerts, Ron Kikinis, Fiona M Fennessy, Andrey Fedorov
Abstract	In this study we assessed the repeatability of the values of radiomics features for small prostate tumors using test-retest Multiparametric Magnetic Resonance Imaging (mpMRI) images. The premise of radiomics is that quantitative image features can serve as biomarkers characterizing disease. For such biomarkers to be useful, repeatability is a basic requirement, meaning its value must remain stable between two scans, if the conditions remain stable. We investigated repeatability of radiomics features under various preprocessing and extraction configurations including various image normalization schemes, different image pre-filtering, 2D vs 3D texture computation, and different bin widths for image discretization. Image registration as means to re-identify regions of interest across time points was evaluated against human-expert segmented regions in both time points. Even though we found many radiomics features and preprocessing combinations with a high repeatability (Intraclass Correlation Coefficient (ICC) > 0.85), our results indicate that overall the repeatability is highly sensitive to the processing parameters (under certain configurations, it can be below 0.0). Image normalization, using a variety of approaches considered, did not result in consistent improvements in repeatability. There was also no consistent improvement of repeatability through the use of pre-filtering options, or by using image registration between timepoints to improve consistency of the region of interest localization. Based on these results we urge caution when interpreting radiomics features and advise paying close attention to the processing configuration details of reported results. Furthermore, we advocate reporting all processing details in radiomics studies and strongly recommend making the implementation available.
Tasks	Image Registration
Published	2018-07-16
URL	http://arxiv.org/abs/1807.06089v2
PDF	http://arxiv.org/pdf/1807.06089v2.pdf
PWC	https://paperswithcode.com/paper/repeatability-of-multiparametric-prostate-mri
Repo	https://github.com/QIICR/QIN-PROSTATE-Repeatability-Radiomics
Framework	none

Improving Transferability of Adversarial Examples with Input Diversity


Title	Improving Transferability of Adversarial Examples with Input Diversity
Authors	Cihang Xie, Zhishuai Zhang, Yuyin Zhou, Song Bai, Jianyu Wang, Zhou Ren, Alan Yuille
Abstract	Though CNNs have achieved the state-of-the-art performance on various vision tasks, they are vulnerable to adversarial examples — crafted by adding human-imperceptible perturbations to clean images. However, most of the existing adversarial attacks only achieve relatively low success rates under the challenging black-box setting, where the attackers have no knowledge of the model structure and parameters. To this end, we propose to improve the transferability of adversarial examples by creating diverse input patterns. Instead of only using the original images to generate adversarial examples, our method applies random transformations to the input images at each iteration. Extensive experiments on ImageNet show that the proposed attack method can generate adversarial examples that transfer much better to different networks than existing baselines. By evaluating our method against top defense solutions and official baselines from NIPS 2017 adversarial competition, the enhanced attack reaches an average success rate of 73.0%, which outperforms the top-1 attack submission in the NIPS competition by a large margin of 6.6%. We hope that our proposed attack strategy can serve as a strong benchmark baseline for evaluating the robustness of networks to adversaries and the effectiveness of different defense methods in the future. Code is available at https://github.com/cihangxie/DI-2-FGSM.
Tasks	Adversarial Attack, Image Classification
Published	2018-03-19
URL	https://arxiv.org/abs/1803.06978v4
PDF	https://arxiv.org/pdf/1803.06978v4.pdf
PWC	https://paperswithcode.com/paper/improving-transferability-of-adversarial
Repo	https://github.com/cihangxie/DI-2-FGSM
Framework	tf