January 31, 2020

3190 words 15 mins read

Paper Group ANR 4

Cherenkov Detectors Fast Simulation Using Neural Networks. Integrating the Data Augmentation Scheme with Various Classifiers for Acoustic Scene Modeling. Estimation of Absolute Scale in Monocular SLAM Using Synthetic Data. FAT Forensics: A Python Toolbox for Algorithmic Fairness, Accountability and Transparency. Fast video object segmentation with …

Cherenkov Detectors Fast Simulation Using Neural Networks


Title	Cherenkov Detectors Fast Simulation Using Neural Networks
Authors	Denis Derkach, Nikita Kazeev, Fedor Ratnikov, Andrey Ustyuzhanin, Alexandra Volokhova
Abstract	We propose a way to simulate Cherenkov detector response using a generative adversarial neural network to bypass low-level details. This network is trained to reproduce high level features of the simulated detector events based on input observables of incident particles. This allows the dramatic increase of simulation speed. We demonstrate that this approach provides simulation precision which is consistent with the baseline and discuss possible implications of these results.
Tasks
Published	2019-03-28
URL	http://arxiv.org/abs/1903.11788v1
PDF	http://arxiv.org/pdf/1903.11788v1.pdf
PWC	https://paperswithcode.com/paper/cherenkov-detectors-fast-simulation-using
Repo
Framework

Integrating the Data Augmentation Scheme with Various Classifiers for Acoustic Scene Modeling


Title	Integrating the Data Augmentation Scheme with Various Classifiers for Acoustic Scene Modeling
Authors	Hangting Chen, Zuozhen Liu, Zongming Liu, Pengyuan Zhang, Yonghong Yan
Abstract	This technical report describes the IOA team’s submission for TASK1A of DCASE2019 challenge. Our acoustic scene classification (ASC) system adopts a data augmentation scheme employing generative adversary networks. Two major classifiers, 1D deep convolutional neural network integrated with scalogram features and 2D fully convolutional neural network integrated with Mel filter bank features, are deployed in the scheme. Other approaches, such as adversary city adaptation, temporal module based on discrete cosine transform and hybrid architectures, have been developed for further fusion. The results of our experiments indicates that the final fusion systems A-D could achieve an accuracy higher than 85% on the officially provided fold 1 evaluation dataset.
Tasks	Acoustic Scene Classification, Data Augmentation, Scene Classification
Published	2019-07-15
URL	https://arxiv.org/abs/1907.06639v1
PDF	https://arxiv.org/pdf/1907.06639v1.pdf
PWC	https://paperswithcode.com/paper/integrating-the-data-augmentation-scheme-with
Repo
Framework

Estimation of Absolute Scale in Monocular SLAM Using Synthetic Data


Title	Estimation of Absolute Scale in Monocular SLAM Using Synthetic Data
Authors	Danila Rukhovich, Daniel Mouritzen, Ralf Kaestner, Martin Rufli, Alexander Velizhev
Abstract	This paper addresses the problem of scale estimation in monocular SLAM by estimating absolute distances between camera centers of consecutive image frames. These estimates would improve the overall performance of classical (not deep) SLAM systems and allow metric feature locations to be recovered from a single monocular camera. We propose several network architectures that lead to an improvement of scale estimation accuracy over the state of the art. In addition, we exploit a possibility to train the neural network only with synthetic data derived from a computer graphics simulator. Our key insight is that, using only synthetic training inputs, we can achieve similar scale estimation accuracy as that obtained from real data. This fact indicates that fully annotated simulated data is a viable alternative to existing deep-learning-based SLAM systems trained on real (unlabeled) data. Our experiments with unsupervised domain adaptation also show that the difference in visual appearance between simulated and real data does not affect scale estimation results. Our method operates with low-resolution images (0.03MP), which makes it practical for real-time SLAM applications with a monocular camera.
Tasks	Domain Adaptation, Unsupervised Domain Adaptation
Published	2019-09-02
URL	https://arxiv.org/abs/1909.00713v1
PDF	https://arxiv.org/pdf/1909.00713v1.pdf
PWC	https://paperswithcode.com/paper/estimation-of-absolute-scale-in-monocular
Repo
Framework

FAT Forensics: A Python Toolbox for Algorithmic Fairness, Accountability and Transparency


Title	FAT Forensics: A Python Toolbox for Algorithmic Fairness, Accountability and Transparency
Authors	Kacper Sokol, Raul Santos-Rodriguez, Peter Flach
Abstract	Machine learning algorithms can take important decisions, sometimes legally binding, about our everyday life. In most cases, however, these systems and decisions are neither regulated nor certified. Given the potential harm that these algorithms can cause, qualities such as fairness, accountability and transparency of predictive systems are of paramount importance. Recent literature suggested voluntary self-reporting on these aspects of predictive systems – e.g., data sheets for data sets – but their scope is often limited to a single component of a machine learning pipeline, and producing them requires manual labour. To resolve this impasse and ensure high-quality, fair, transparent and reliable machine learning systems, we developed an open source toolbox that can inspect selected fairness, accountability and transparency aspects of these systems to automatically and objectively report them back to their engineers and users. We describe design, scope and usage examples of this Python toolbox in this paper. The toolbox provides functionality for inspecting fairness, accountability and transparency of all aspects of the machine learning process: data (and their features), models and predictions. It is available to the public under the BSD 3-Clause open source licence.
Tasks
Published	2019-09-11
URL	https://arxiv.org/abs/1909.05167v1
PDF	https://arxiv.org/pdf/1909.05167v1.pdf
PWC	https://paperswithcode.com/paper/fat-forensics-a-python-toolbox-for
Repo
Framework

Fast video object segmentation with Spatio-Temporal GANs


Title	Fast video object segmentation with Spatio-Temporal GANs
Authors	Sergi Caelles, Albert Pumarola, Francesc Moreno-Noguer, Alberto Sanfeliu, Luc Van Gool
Abstract	Learning descriptive spatio-temporal object models from data is paramount for the task of semi-supervised video object segmentation. Most existing approaches mainly rely on models that estimate the segmentation mask based on a reference mask at the first frame (aided sometimes by optical flow or the previous mask). These models, however, are prone to fail under rapid appearance changes or occlusions due to their limitations in modelling the temporal component. On the other hand, very recently, other approaches learned long-term features using a convolutional LSTM to leverage the information from all previous video frames. Even though these models achieve better temporal representations, they still have to be fine-tuned for every new video sequence. In this paper, we present an intermediate solution and devise a novel GAN architecture, FaSTGAN, to learn spatio-temporal object models over finite temporal windows. To achieve this, we concentrate all the heavy computational load to the training phase with two critics that enforce spatial and temporal mask consistency over the last K frames. Then at test time, we only use a relatively light regressor, which reduces the inference time considerably. As a result, our approach combines a high resiliency to sudden geometric and photometric object changes with efficiency at test time (no need for fine-tuning nor post-processing). We demonstrate that the accuracy of our method is on par with state-of-the-art techniques on the challenging YouTube-VOS and DAVIS datasets, while running at 32 fps, about 4x faster than the closest competitor.
Tasks	Optical Flow Estimation, Semantic Segmentation, Semi-supervised Video Object Segmentation, Video Object Segmentation, Video Semantic Segmentation
Published	2019-03-28
URL	http://arxiv.org/abs/1903.12161v1
PDF	http://arxiv.org/pdf/1903.12161v1.pdf
PWC	https://paperswithcode.com/paper/fast-video-object-segmentation-with-spatio
Repo
Framework

PartNet: A Recursive Part Decomposition Network for Fine-grained and Hierarchical Shape Segmentation


Title	PartNet: A Recursive Part Decomposition Network for Fine-grained and Hierarchical Shape Segmentation
Authors	Fenggen Yu, Kun Liu, Yan Zhang, Chenyang Zhu, Kai Xu
Abstract	Deep learning approaches to 3D shape segmentation are typically formulated as a multi-class labeling problem. Existing models are trained for a fixed set of labels, which greatly limits their flexibility and adaptivity. We opt for top-down recursive decomposition and develop the first deep learning model for hierarchical segmentation of 3D shapes, based on recursive neural networks. Starting from a full shape represented as a point cloud, our model performs recursive binary decomposition, where the decomposition network at all nodes in the hierarchy share weights. At each node, a node classifier is trained to determine the type (adjacency or symmetry) and stopping criteria of its decomposition. The features extracted in higher level nodes are recursively propagated to lower level ones. Thus, the meaningful decompositions in higher levels provide strong contextual cues constraining the segmentations in lower levels. Meanwhile, to increase the segmentation accuracy at each node, we enhance the recursive contextual feature with the shape feature extracted for the corresponding part. Our method segments a 3D shape in point cloud into an unfixed number of parts, depending on the shape complexity, showing strong generality and flexibility. It achieves the state-of-the-art performance, both for fine-grained and semantic segmentation, on the public benchmark and a new benchmark of fine-grained segmentation proposed in this work. We also demonstrate its application for fine-grained part refinements in image-to-shape reconstruction.
Tasks	Semantic Segmentation
Published	2019-03-02
URL	http://arxiv.org/abs/1903.00709v4
PDF	http://arxiv.org/pdf/1903.00709v4.pdf
PWC	https://paperswithcode.com/paper/partnet-a-recursive-part-decomposition
Repo
Framework

Multi-Scale Attentional Network for Multi-Focal Segmentation of Active Bleed after Pelvic Fractures


Title	Multi-Scale Attentional Network for Multi-Focal Segmentation of Active Bleed after Pelvic Fractures
Authors	Yuyin Zhou, David Dreizin, Yingwei Li, Zhishuai Zhang, Yan Wang, Alan Yuille
Abstract	Trauma is the worldwide leading cause of death and disability in those younger than 45 years, and pelvic fractures are a major source of morbidity and mortality. Automated segmentation of multiple foci of arterial bleeding from abdominopelvic trauma CT could provide rapid objective measurements of the total extent of active bleeding, potentially augmenting outcome prediction at the point of care, while improving patient triage, allocation of appropriate resources, and time to definitive intervention. In spite of the importance of active bleeding in the quick tempo of trauma care, the task is still quite challenging due to the variable contrast, intensity, location, size, shape, and multiplicity of bleeding foci. Existing work [4] presents a heuristic rule-based segmentation technique which requires multiple stages and cannot be efficiently optimized end-to-end. To this end, we present, Multi-Scale Attentional Network (MSAN), the first yet reliable end-to-end network, for automated segmentation of active hemorrhage from contrast-enhanced trauma CT scans. MSAN consists of the following components: 1) an encoder which fully integrates the global contextual information from holistic 2D slices; 2) a multi-scale strategy applied both in the training stage and the inference stage to handle the challenges induced by variation of target sizes; 3) an attentional module to further refine the deep features, leading to better segmentation quality; and 4) a multi-view mechanism to fully leverage the 3D information. Our MSAN reports a significant improvement of more than 7% compared to prior arts in terms of DSC.
Tasks
Published	2019-06-23
URL	https://arxiv.org/abs/1906.09540v2
PDF	https://arxiv.org/pdf/1906.09540v2.pdf
PWC	https://paperswithcode.com/paper/multi-scale-attentional-network-for-multi
Repo
Framework

Efficient MCMC Sampling with Dimension-Free Convergence Rate using ADMM-type Splitting


Title	Efficient MCMC Sampling with Dimension-Free Convergence Rate using ADMM-type Splitting
Authors	Maxime Vono, Daniel Paulin, Arnaud Doucet
Abstract	Performing exact Bayesian inference for complex models is intractable. Markov chain Monte Carlo (MCMC) algorithms can provide reliable approximations of the posterior distribution but are computationally expensive for large datasets. A standard approach to mitigate this complexity consists of using subsampling techniques or distributing the data across a cluster. However, these approaches are typically unreliable in high-dimensional scenarios. We focus here on an alternative class of MCMC schemes exploiting a splitting strategy akin to the one used by the celebrated ADMM optimization algorithm. These methods, proposed recently in [43, 51], appear to provide empirically state-of-the-art performance. We generalize here these ideas and propose a detailed theoretical study of one of these algorithms known as the Split Gibbs Sampler. Under regularity conditions, we establish explicit dimension-free convergence rates for this scheme using Ricci curvature and coupling ideas. We demonstrate experimentally the excellent performance of these MCMC schemes on various applications.
Tasks	Bayesian Inference
Published	2019-05-23
URL	https://arxiv.org/abs/1905.11937v2
PDF	https://arxiv.org/pdf/1905.11937v2.pdf
PWC	https://paperswithcode.com/paper/190511937
Repo
Framework

Complexity Bounds for the Controllability of Temporal Networks with Conditions, Disjunctions, and Uncertainty


Title	Complexity Bounds for the Controllability of Temporal Networks with Conditions, Disjunctions, and Uncertainty
Authors	Nikhil Bhargava, Brian Williams
Abstract	In temporal planning, many different temporal network formalisms are used to model real world situations. Each of these formalisms has different features which affect how easy it is to determine whether the underlying network of temporal constraints is consistent. While many of the simpler models have been well-studied from a computational complexity perspective, the algorithms developed for advanced models which combine features have very loose complexity bounds. In this paper, we provide tight completeness bounds for strong, weak, and dynamic controllability checking of temporal networks that have conditions, disjunctions, and temporal uncertainty. Our work exposes some of the subtle differences between these different structures and, remarkably, establishes a guarantee that all of these problems are computable in PSPACE.
Tasks
Published	2019-01-08
URL	http://arxiv.org/abs/1901.02307v1
PDF	http://arxiv.org/pdf/1901.02307v1.pdf
PWC	https://paperswithcode.com/paper/complexity-bounds-for-the-controllability-of
Repo
Framework

LR-GLM: High-Dimensional Bayesian Inference Using Low-Rank Data Approximations


Title	LR-GLM: High-Dimensional Bayesian Inference Using Low-Rank Data Approximations
Authors	Brian L. Trippe, Jonathan H. Huggins, Raj Agrawal, Tamara Broderick
Abstract	Due to the ease of modern data collection, applied statisticians often have access to a large set of covariates that they wish to relate to some observed outcome. Generalized linear models (GLMs) offer a particularly interpretable framework for such an analysis. In these high-dimensional problems, the number of covariates is often large relative to the number of observations, so we face non-trivial inferential uncertainty; a Bayesian approach allows coherent quantification of this uncertainty. Unfortunately, existing methods for Bayesian inference in GLMs require running times roughly cubic in parameter dimension, and so are limited to settings with at most tens of thousand parameters. We propose to reduce time and memory costs with a low-rank approximation of the data in an approach we call LR-GLM. When used with the Laplace approximation or Markov chain Monte Carlo, LR-GLM provides a full Bayesian posterior approximation and admits running times reduced by a full factor of the parameter dimension. We rigorously establish the quality of our approximation and show how the choice of rank allows a tunable computational-statistical trade-off. Experiments support our theory and demonstrate the efficacy of LR-GLM on real large-scale datasets.
Tasks	Bayesian Inference
Published	2019-05-17
URL	https://arxiv.org/abs/1905.07499v1
PDF	https://arxiv.org/pdf/1905.07499v1.pdf
PWC	https://paperswithcode.com/paper/lr-glm-high-dimensional-bayesian-inference
Repo
Framework

Learning Super-resolved Depth from Active Gated Imaging


Title	Learning Super-resolved Depth from Active Gated Imaging
Authors	Tobias Gruber, Mariia Kokhova, Werner Ritter, Norbert Haala, Klaus Dietmayer
Abstract	Environment perception for autonomous driving is doomed by the trade-off between range-accuracy and resolution: current sensors that deliver very precise depth information are usually restricted to low resolution because of technology or cost limitations. In this work, we exploit depth information from an active gated imaging system based on cost-sensitive diode and CMOS technology. Learning a mapping between pixel intensities of three gated slices and depth produces a super-resolved depth map image with respectable relative accuracy of 5% in between 25-80 m. By design, depth information is perfectly aligned with pixel intensity values.
Tasks	Autonomous Driving
Published	2019-12-05
URL	https://arxiv.org/abs/1912.02889v1
PDF	https://arxiv.org/pdf/1912.02889v1.pdf
PWC	https://paperswithcode.com/paper/learning-super-resolved-depth-from-active
Repo
Framework

Action Recognition Using Supervised Spiking Neural Networks


Title	Action Recognition Using Supervised Spiking Neural Networks
Authors	Aref Moqadam Mehr, Saeed Reza Kheradpisheh, Hadi Farahani
Abstract	Biological neurons use spikes to process and learn temporally dynamic inputs in an energy and computationally efficient way. However, applying the state-of-the-art gradient-based supervised algorithms to spiking neural networks (SNN) is a challenge due to the non-differentiability of the activation function of spiking neurons. Employing surrogate gradients is one of the main solutions to overcome this challenge. Although SNNs naturally work in the temporal domain, recent studies have focused on developing SNNs to solve static image categorization tasks. In this paper, we employ a surrogate gradient descent learning algorithm to recognize twelve human hand gestures recorded by dynamic vision sensor (DVS) cameras. The proposed SNN could reach 97.2% recognition accuracy on test data.
Tasks	Image Categorization
Published	2019-11-09
URL	https://arxiv.org/abs/1911.03630v2
PDF	https://arxiv.org/pdf/1911.03630v2.pdf
PWC	https://paperswithcode.com/paper/action-recognition-using-supervised-spiking
Repo
Framework

Few-Shot Learning with Per-Sample Rich Supervision


Title	Few-Shot Learning with Per-Sample Rich Supervision
Authors	Roman Visotsky, Yuval Atzmon, Gal Chechik
Abstract	Learning with few samples is a major challenge for parameter-rich models like deep networks. In contrast, people learn complex new concepts even from very few examples, suggesting that the sample complexity of learning can often be reduced. Many approaches to few-shot learning build on transferring a representation from well-sampled classes, or using meta learning to favor architectures that can learn with few samples. Unfortunately, such approaches often struggle when learning in an online way or with non-stationary data streams. Here we describe a new approach to learn with fewer samples, by using additional information that is provided per sample. Specifically, we show how the sample complexity can be reduced by providing semantic information about the relevance of features per sample, like information about the presence of objects in a scene or confidence of detecting attributes in an image. We provide an improved generalization error bound for this case. We cast the problem of using per-sample feature relevance by using a new ellipsoid-margin loss, and develop an online algorithm that minimizes this loss effectively. Empirical evaluation on two machine vision benchmarks for scene classification and fine-grain bird classification demonstrate the benefits of this approach for few-shot learning.
Tasks	Few-Shot Learning, Meta-Learning, Scene Classification
Published	2019-06-10
URL	https://arxiv.org/abs/1906.03859v1
PDF	https://arxiv.org/pdf/1906.03859v1.pdf
PWC	https://paperswithcode.com/paper/few-shot-learning-with-per-sample-rich
Repo
Framework

Asymptotic Guarantees for Learning Generative Models with the Sliced-Wasserstein Distance


Title	Asymptotic Guarantees for Learning Generative Models with the Sliced-Wasserstein Distance
Authors	Kimia Nadjahi, Alain Durmus, Umut Şimşekli, Roland Badeau
Abstract	Minimum expected distance estimation (MEDE) algorithms have been widely used for probabilistic models with intractable likelihood functions and they have become increasingly popular due to their use in implicit generative modeling (e.g. Wasserstein generative adversarial networks, Wasserstein autoencoders). Emerging from computational optimal transport, the Sliced-Wasserstein (SW) distance has become a popular choice in MEDE thanks to its simplicity and computational benefits. While several studies have reported empirical success on generative modeling with SW, the theoretical properties of such estimators have not yet been established. In this study, we investigate the asymptotic properties of estimators that are obtained by minimizing SW. We first show that convergence in SW implies weak convergence of probability measures in general Wasserstein spaces. Then we show that estimators obtained by minimizing SW (and also an approximate version of SW) are asymptotically consistent. We finally prove a central limit theorem, which characterizes the asymptotic distribution of the estimators and establish a convergence rate of $\sqrt{n}$, where $n$ denotes the number of observed data points. We illustrate the validity of our theory on both synthetic data and neural networks.
Tasks
Published	2019-06-11
URL	https://arxiv.org/abs/1906.04516v2
PDF	https://arxiv.org/pdf/1906.04516v2.pdf
PWC	https://paperswithcode.com/paper/asymptotic-guarantees-for-learning-generative
Repo
Framework

Nonstationary Nonparametric Online Learning: Balancing Dynamic Regret and Model Parsimony


Title	Nonstationary Nonparametric Online Learning: Balancing Dynamic Regret and Model Parsimony
Authors	Amrit Singh Bedi, Alec Koppel, Ketan Rajawat, Brian M. Sadler
Abstract	An open challenge in supervised learning is \emph{conceptual drift}: a data point begins as classified according to one label, but over time the notion of that label changes. Beyond linear autoregressive models, transfer and meta learning address drift, but require data that is representative of disparate domains at the outset of training. To relax this requirement, we propose a memory-efficient \emph{online} universal function approximator based on compressed kernel methods. Our approach hinges upon viewing non-stationary learning as online convex optimization with dynamic comparators, for which performance is quantified by dynamic regret. Prior works control dynamic regret growth only for linear models. In contrast, we hypothesize actions belong to reproducing kernel Hilbert spaces (RKHS). We propose a functional variant of online gradient descent (OGD) operating in tandem with greedy subspace projections. Projections are necessary to surmount the fact that RKHS functions have complexity proportional to time. For this scheme, we establish sublinear dynamic regret growth in terms of both loss variation and functional path length, and that the memory of the function sequence remains moderate. Experiments demonstrate the usefulness of the proposed technique for online nonlinear regression and classification problems with non-stationary data.
Tasks	Meta-Learning
Published	2019-09-12
URL	https://arxiv.org/abs/1909.05442v1
PDF	https://arxiv.org/pdf/1909.05442v1.pdf
PWC	https://paperswithcode.com/paper/nonstationary-nonparametric-online-learning
Repo
Framework