October 20, 2019

3425 words 17 mins read

Paper Group AWR 350

Differentially Private Bayesian Inference for Exponential Families. Evolving Multimodal Robot Behavior via Many Stepping Stones with the Combinatorial Multi-Objective Evolutionary Algorithm. Found Graph Data and Planted Vertex Covers. Deblending galaxy superpositions with branched generative adversarial networks. Scientific image rendering for spac …

Differentially Private Bayesian Inference for Exponential Families


Title	Differentially Private Bayesian Inference for Exponential Families
Authors	Garrett Bernstein, Daniel Sheldon
Abstract	The study of private inference has been sparked by growing concern regarding the analysis of data when it stems from sensitive sources. We present the first method for private Bayesian inference in exponential families that properly accounts for noise introduced by the privacy mechanism. It is efficient because it works only with sufficient statistics and not individual data. Unlike other methods, it gives properly calibrated posterior beliefs in the non-asymptotic data regime.
Tasks	Bayesian Inference
Published	2018-09-06
URL	http://arxiv.org/abs/1809.02188v3
PDF	http://arxiv.org/pdf/1809.02188v3.pdf
PWC	https://paperswithcode.com/paper/differentially-private-bayesian-inference-for
Repo	https://github.com/gbernstein6/private_bayesian_expfam
Framework	none

Evolving Multimodal Robot Behavior via Many Stepping Stones with the Combinatorial Multi-Objective Evolutionary Algorithm


Title	Evolving Multimodal Robot Behavior via Many Stepping Stones with the Combinatorial Multi-Objective Evolutionary Algorithm
Authors	Joost Huizinga, Jeff Clune
Abstract	An important challenge in reinforcement learning, including evolutionary robotics, is to solve multimodal problems, where agents have to act in qualitatively different ways depending on the circumstances. Because multimodal problems are often too difficult to solve directly, it is helpful to take advantage of staging, where a difficult task is divided into simpler subtasks that can serve as stepping stones for solving the overall problem. Unfortunately, choosing an effective ordering for these subtasks is difficult, and a poor ordering can reduce the speed and performance of the learning process. Here, we provide a thorough introduction and investigation of the Combinatorial Multi-Objective Evolutionary Algorithm (CMOEA), which avoids ordering subtasks by allowing all combinations of subtasks to be explored simultaneously. We compare CMOEA against two algorithms that can similarly optimize on multiple subtasks simultaneously: NSGA-II and Lexicase Selection. The algorithms are tested on a multimodal robotics problem with six subtasks as well as a maze navigation problem with a hundred subtasks. On these problems, CMOEA either outperforms or is competitive with the controls. Separately, we show that adding a linear combination over all objectives can improve the ability of NSGA-II to solve these multimodal problems. Lastly, we show that, in contrast to NSGA-II and Lexicase Selection, CMOEA can effectively leverage secondary objectives to achieve state-of-the-art results on the robotics task. In general, our experiments suggest that CMOEA is a promising, state-of-the-art algorithm for solving multimodal problems.
Tasks
Published	2018-07-09
URL	https://arxiv.org/abs/1807.03392v2
PDF	https://arxiv.org/pdf/1807.03392v2.pdf
PWC	https://paperswithcode.com/paper/evolving-multimodal-robot-behavior-via-many
Repo	https://github.com/Evolving-AI-Lab/cmoea
Framework	none

Found Graph Data and Planted Vertex Covers


Title	Found Graph Data and Planted Vertex Covers
Authors	Austin R. Benson, Jon Kleinberg
Abstract	A typical way in which network data is recorded is to measure all the interactions among a specified set of core nodes; this produces a graph containing this core together with a potentially larger set of fringe nodes that have links to the core. Interactions between pairs of nodes in the fringe, however, are not recorded by this process, and hence not present in the resulting graph data. For example, a phone service provider may only have records of calls in which at least one of the participants is a customer; this can include calls between a customer and a non-customer, but not between pairs of non-customers. Knowledge of which nodes belong to the core is an important piece of metadata that is crucial for interpreting the network dataset. But in many cases, this metadata is not available, either because it has been lost due to difficulties in data provenance, or because the network consists of found data obtained in settings such as counter-surveillance. This leads to a natural algorithmic problem, namely the recovery of the core set. Since the core set forms a vertex cover of the graph, we essentially have a planted vertex cover problem, but with an arbitrary underlying graph. We develop a theoretical framework for analyzing this planted vertex cover problem, based on results in the theory of fixed-parameter tractability, together with algorithms for recovering the core. Our algorithms are fast, simple to implement, and out-perform several methods based on network core-periphery structure on various real-world datasets.
Tasks
Published	2018-05-03
URL	http://arxiv.org/abs/1805.01209v1
PDF	http://arxiv.org/pdf/1805.01209v1.pdf
PWC	https://paperswithcode.com/paper/found-graph-data-and-planted-vertex-covers
Repo	https://github.com/arbenson/FGDnPVC
Framework	none

Deblending galaxy superpositions with branched generative adversarial networks


Title	Deblending galaxy superpositions with branched generative adversarial networks
Authors	David M. Reiman, Brett E. Göhre
Abstract	Near-future large galaxy surveys will encounter blended galaxy images at a fraction of up to 50% in the densest regions of the universe. Current deblending techniques may segment the foreground galaxy while leaving missing pixel intensities in the background galaxy flux. The problem is compounded by the diffuse nature of galaxies in their outer regions, making segmentation significantly more difficult than in traditional object segmentation applications. We propose a novel branched generative adversarial network (GAN) to deblend overlapping galaxies, where the two branches produce images of the two deblended galaxies. We show that generative models are a powerful engine for deblending given their innate ability to infill missing pixel values occluded by the superposition. We maintain high peak signal-to-noise ratio and structural similarity scores with respect to ground truth images upon deblending. Our model also predicts near-instantaneously, making it a natural choice for the immense quantities of data soon to be created by large surveys such as LSST, Euclid and WFIRST.
Tasks	Semantic Segmentation
Published	2018-10-23
URL	http://arxiv.org/abs/1810.10098v4
PDF	http://arxiv.org/pdf/1810.10098v4.pdf
PWC	https://paperswithcode.com/paper/deblending-galaxy-superpositions-with
Repo	https://github.com/davidreiman/deblender
Framework	tf

Scientific image rendering for space scenes with the SurRender software


Title	Scientific image rendering for space scenes with the SurRender software
Authors	Roland Brochard, Jérémy Lebreton, Cyril Robin, Keyvan Kanani, Grégory Jonniaux, Aurore Masson, Noela Despré, Ahmad Berjaoui
Abstract	Spacecraft autonomy can be enhanced by vision-based navigation (VBN) techniques. Applications range from manoeuvers around Solar System objects and landing on planetary surfaces, to in-orbit servicing or space debris removal. The development and validation of VBN algorithms relies on the availability of physically accurate relevant images. Yet archival data from past missions can rarely serve this purpose and acquiring new data is often costly. The SurRender software is an image simulator that addresses the challenges of realistic image rendering, with high representativeness for space scenes. Images are rendered by raytracing, which implements the physical principles of geometrical light propagation, in physical units. A macroscopic instrument model and scene objects reflectance functions are used. SurRender is specially optimized for space scenes, with huge distances between objects and scenes up to Solar System size. Raytracing conveniently tackles some important effects for VBN algorithms: image quality, eclipses, secondary illumination, subpixel limb imaging, etc. A simulation is easily setup (in MATLAB, Python, and more) by specifying the position of the bodies (camera, Sun, planets, satellites) over time, 3D shapes and material surface properties. SurRender comes with its own modelling tool enabling to go beyond existing models for shapes, materials and sensors (projection, temporal sampling, electronics, etc.). It is natively designed to simulate different kinds of sensors (visible, LIDAR, etc.). Tools are available for manipulating huge datasets to store albedo maps and digital elevation models, or for procedural (fractal) texturing that generates high-quality images for a large range of observing distances (from millions of km to touchdown). We illustrate SurRender performances with a selection of case studies, placing particular emphasis on a 900-km Moon flyby simulation.
Tasks
Published	2018-10-02
URL	http://arxiv.org/abs/1810.01423v1
PDF	http://arxiv.org/pdf/1810.01423v1.pdf
PWC	https://paperswithcode.com/paper/scientific-image-rendering-for-space-scenes
Repo	https://github.com/SurRenderSoftware/surrender_client_API
Framework	none

Detection-Tracking for Efficient Person Analysis: The DetTA Pipeline


Title	Detection-Tracking for Efficient Person Analysis: The DetTA Pipeline
Authors	Stefan Breuers, Lucas Beyer, Umer Rafi, Bastian Leibe
Abstract	In the past decade many robots were deployed in the wild, and people detection and tracking is an important component of such deployments. On top of that, one often needs to run modules which analyze persons and extract higher level attributes such as age and gender, or dynamic information like gaze and pose. The latter ones are especially necessary for building a reactive, social robot-person interaction. In this paper, we combine those components in a fully modular detection-tracking-analysis pipeline, called DetTA. We investigate the benefits of such an integration on the example of head and skeleton pose, by using the consistent track ID for a temporal filtering of the analysis modules’ observations, showing a slight improvement in a challenging real-world scenario. We also study the potential of a so-called “free-flight” mode, where the analysis of a person attribute only relies on the filter’s predictions for certain frames. Here, our study shows that this boosts the runtime dramatically, while the prediction quality remains stable. This insight is especially important for reducing power consumption and sharing precious (GPU-)memory when running many analysis components on a mobile platform, especially so in the era of expensive deep learning methods.
Tasks
Published	2018-04-26
URL	http://arxiv.org/abs/1804.10134v2
PDF	http://arxiv.org/pdf/1804.10134v2.pdf
PWC	https://paperswithcode.com/paper/detection-tracking-for-efficient-person
Repo	https://github.com/sbreuers/detta
Framework	none

LRW-1000: A Naturally-Distributed Large-Scale Benchmark for Lip Reading in the Wild


Title	LRW-1000: A Naturally-Distributed Large-Scale Benchmark for Lip Reading in the Wild
Authors	Shuang Yang, Yuanhang Zhang, Dalu Feng, Mingmin Yang, Chenhao Wang, Jingyun Xiao, Keyu Long, Shiguang Shan, Xilin Chen
Abstract	Large-scale datasets have successively proven their fundamental importance in several research fields, especially for early progress in some emerging topics. In this paper, we focus on the problem of visual speech recognition, also known as lipreading, which has received increasing interest in recent years. We present a naturally-distributed large-scale benchmark for lip reading in the wild, named LRW-1000, which contains 1,000 classes with 718,018 samples from more than 2,000 individual speakers. Each class corresponds to the syllables of a Mandarin word composed of one or several Chinese characters. To the best of our knowledge, it is currently the largest word-level lipreading dataset and also the only public large-scale Mandarin lipreading dataset. This dataset aims at covering a “natural” variability over different speech modes and imaging conditions to incorporate challenges encountered in practical applications. It has shown a large variation in this benchmark in several aspects, including the number of samples in each class, video resolution, lighting conditions, and speakers’ attributes such as pose, age, gender, and make-up. Besides providing a detailed description of the dataset and its collection pipeline, we evaluate several typical popular lipreading methods and perform a thorough analysis of the results from several aspects. The results demonstrate the consistency and challenges of our dataset, which may open up some new promising directions for future work.
Tasks	Lipreading, Speech Recognition, Visual Speech Recognition
Published	2018-10-16
URL	http://arxiv.org/abs/1810.06990v6
PDF	http://arxiv.org/pdf/1810.06990v6.pdf
PWC	https://paperswithcode.com/paper/lrw-1000-a-naturally-distributed-large-scale
Repo	https://github.com/Fengdalu/Lipreading-DenseNet3D
Framework	pytorch

Safe Option-Critic: Learning Safety in the Option-Critic Architecture


Title	Safe Option-Critic: Learning Safety in the Option-Critic Architecture
Authors	Arushi Jain, Khimya Khetarpal, Doina Precup
Abstract	Designing hierarchical reinforcement learning algorithms that induce a notion of safety is not only vital for safety-critical applications, but also, brings better understanding of an artificially intelligent agent’s decisions. While learning end-to-end options automatically has been fully realized recently, we propose a solution to learning safe options. We introduce the idea of controllability of states based on the temporal difference errors in the option-critic framework. We then derive the policy-gradient theorem with controllability and propose a novel framework called safe option-critic. We demonstrate the effectiveness of our approach in the four-rooms grid-world, cartpole, and three games in the Arcade Learning Environment (ALE): MsPacman, Amidar and Q*Bert. Learning of end-to-end options with the proposed notion of safety achieves reduction in the variance of return and boosts the performance in environments with intrinsic variability in the reward structure. More importantly, the proposed algorithm outperforms the vanilla options in all the environments and primitive actions in two out of three ALE games.
Tasks	Atari Games, Hierarchical Reinforcement Learning
Published	2018-07-21
URL	http://arxiv.org/abs/1807.08060v1
PDF	http://arxiv.org/pdf/1807.08060v1.pdf
PWC	https://paperswithcode.com/paper/safe-option-critic-learning-safety-in-the
Repo	https://github.com/arushi12130/SafeOptionCritic
Framework	none

Unsupervised adversarial domain adaptation for acoustic scene classification


Title	Unsupervised adversarial domain adaptation for acoustic scene classification
Authors	Shayan Gharib, Konstantinos Drossos, Emre Çakir, Dmitriy Serdyuk, Tuomas Virtanen
Abstract	A general problem in acoustic scene classification task is the mismatched conditions between training and testing data, which significantly reduces the performance of the developed methods on classification accuracy. As a countermeasure, we present the first method of unsupervised adversarial domain adaptation for acoustic scene classification. We employ a model pre-trained on data from one set of conditions and by using data from other set of conditions, we adapt the model in order that its output cannot be used for classifying the set of conditions that input data belong to. We use a freely available dataset from the DCASE 2018 challenge Task 1, subtask B, that contains data from mismatched recording devices. We consider the scenario where the annotations are available for the data recorded from one device, but not for the rest. Our results show that with our model agnostic method we can achieve $\sim 10%$ increase at the accuracy on an unseen and unlabeled dataset, while keeping almost the same performance on the labeled dataset.
Tasks	Acoustic Scene Classification, Domain Adaptation, Scene Classification
Published	2018-08-17
URL	http://arxiv.org/abs/1808.05777v1
PDF	http://arxiv.org/pdf/1808.05777v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-adversarial-domain-adaptation
Repo	https://github.com/shayangharib/AUDASC
Framework	pytorch

Stochastic Wasserstein Barycenters


Title	Stochastic Wasserstein Barycenters
Authors	Sebastian Claici, Edward Chien, Justin Solomon
Abstract	We present a stochastic algorithm to compute the barycenter of a set of probability distributions under the Wasserstein metric from optimal transport. Unlike previous approaches, our method extends to continuous input distributions and allows the support of the barycenter to be adjusted in each iteration. We tackle the problem without regularization, allowing us to recover a sharp output whose support is contained within the support of the true barycenter. We give examples where our algorithm recovers a more meaningful barycenter than previous work. Our method is versatile and can be extended to applications such as generating super samples from a given distribution and recovering blue noise approximations.
Tasks
Published	2018-02-15
URL	http://arxiv.org/abs/1802.05757v3
PDF	http://arxiv.org/pdf/1802.05757v3.pdf
PWC	https://paperswithcode.com/paper/stochastic-wasserstein-barycenters
Repo	https://github.com/gparracl/StochasticWassersteinBarycenter
Framework	tf

PeerNets: Exploiting Peer Wisdom Against Adversarial Attacks


Title	PeerNets: Exploiting Peer Wisdom Against Adversarial Attacks
Authors	Jan Svoboda, Jonathan Masci, Federico Monti, Michael M. Bronstein, Leonidas Guibas
Abstract	Deep learning systems have become ubiquitous in many aspects of our lives. Unfortunately, it has been shown that such systems are vulnerable to adversarial attacks, making them prone to potential unlawful uses. Designing deep neural networks that are robust to adversarial attacks is a fundamental step in making such systems safer and deployable in a broader variety of applications (e.g. autonomous driving), but more importantly is a necessary step to design novel and more advanced architectures built on new computational paradigms rather than marginally building on the existing ones. In this paper we introduce PeerNets, a novel family of convolutional networks alternating classical Euclidean convolutions with graph convolutions to harness information from a graph of peer samples. This results in a form of non-local forward propagation in the model, where latent features are conditioned on the global structure induced by the graph, that is up to 3 times more robust to a variety of white- and black-box adversarial attacks compared to conventional architectures with almost no drop in accuracy.
Tasks	Autonomous Driving
Published	2018-05-31
URL	http://arxiv.org/abs/1806.00088v1
PDF	http://arxiv.org/pdf/1806.00088v1.pdf
PWC	https://paperswithcode.com/paper/peernets-exploiting-peer-wisdom-against
Repo	https://github.com/tantara/PeerNets-pytorch
Framework	pytorch

Deep Convolutional Networks as shallow Gaussian Processes


Title	Deep Convolutional Networks as shallow Gaussian Processes
Authors	Adrià Garriga-Alonso, Carl Edward Rasmussen, Laurence Aitchison
Abstract	We show that the output of a (residual) convolutional neural network (CNN) with an appropriate prior over the weights and biases is a Gaussian process (GP) in the limit of infinitely many convolutional filters, extending similar results for dense networks. For a CNN, the equivalent kernel can be computed exactly and, unlike “deep kernels”, has very few parameters: only the hyperparameters of the original CNN. Further, we show that this kernel has two properties that allow it to be computed efficiently; the cost of evaluating the kernel for a pair of images is similar to a single forward pass through the original CNN with only one filter per layer. The kernel equivalent to a 32-layer ResNet obtains 0.84% classification error on MNIST, a new record for GPs with a comparable number of parameters.
Tasks	Gaussian Processes
Published	2018-08-16
URL	https://arxiv.org/abs/1808.05587v2
PDF	https://arxiv.org/pdf/1808.05587v2.pdf
PWC	https://paperswithcode.com/paper/deep-convolutional-networks-as-shallow
Repo	https://github.com/convnets-as-gps/convnets-as-gps
Framework	tf

LadderNet: Multi-path networks based on U-Net for medical image segmentation


Title	LadderNet: Multi-path networks based on U-Net for medical image segmentation
Authors	Juntang Zhuang
Abstract	U-Net has been providing state-of-the-art performance in many medical image segmentation problems. Many modifications have been proposed for U-Net, such as attention U-Net, recurrent residual convolutional U-Net (R2-UNet), and U-Net with residual blocks or blocks with dense connections. However, all these modifications have an encoder-decoder structure with skip connections, and the number of paths for information flow is limited. We propose LadderNet in this paper, which can be viewed as a chain of multiple U-Nets. Instead of only one pair of encoder branch and decoder branch in U-Net, a LadderNet has multiple pairs of encoder-decoder branches, and has skip connections between every pair of adjacent decoder and decoder branches in each level. Inspired by the success of ResNet and R2-UNet, we use modified residual blocks where two convolutional layers in one block share the same weights. A LadderNet has more paths for information flow because of skip connections and residual blocks, and can be viewed as an ensemble of Fully Convolutional Networks (FCN). The equivalence to an ensemble of FCNs improves segmentation accuracy, while the shared weights within each residual block reduce parameter number. Semantic segmentation is essential for retinal disease detection. We tested LadderNet on two benchmark datasets for blood vessel segmentation in retinal images, and achieved superior performance over methods in the literature. The implementation is provided \url{https://github.com/juntang-zhuang/LadderNet}
Tasks	Medical Image Segmentation, Retinal Vessel Segmentation, Semantic Segmentation
Published	2018-10-17
URL	https://arxiv.org/abs/1810.07810v4
PDF	https://arxiv.org/pdf/1810.07810v4.pdf
PWC	https://paperswithcode.com/paper/laddernet-multi-path-networks-based-on-u-net
Repo	https://github.com/juntang-zhuang/LadderNet
Framework	pytorch

Stable Gaussian Process based Tracking Control of Euler-Lagrange Systems


Title	Stable Gaussian Process based Tracking Control of Euler-Lagrange Systems
Authors	Thomas Beckers, Dana Kulić, Sandra Hirche
Abstract	Perfect tracking control for real-world Euler-Lagrange systems is challenging due to uncertainties in the system model and external disturbances. The magnitude of the tracking error can be reduced either by increasing the feedback gains or improving the model of the system. The latter is clearly preferable as it allows to maintain good tracking performance at low feedback gains. However, accurate models are often difficult to obtain. In this article, we address the problem of stable high-performance tracking control for unknown Euler-Lagrange systems. In particular, we employ Gaussian Process regression to obtain a data-driven model that is used for the feed-forward compensation of unknown dynamics of the system. The model fidelity is used to adapt the feedback gains allowing low feedback gains in state space regions of high model confidence. The proposed control law guarantees a globally bounded tracking error with a specific probability. Simulation studies demonstrate the superiority over state of the art tracking control approaches.
Tasks
Published	2018-06-19
URL	http://arxiv.org/abs/1806.07190v2
PDF	http://arxiv.org/pdf/1806.07190v2.pdf
PWC	https://paperswithcode.com/paper/stable-gaussian-process-based-tracking
Repo	https://github.com/TBeckers/CTC_GPR
Framework	none

Reconciling $λ$-Returns with Experience Replay


Title	Reconciling $λ$-Returns with Experience Replay
Authors	Brett Daley, Christopher Amato
Abstract	Modern deep reinforcement learning methods have departed from the incremental learning required for eligibility traces, rendering the implementation of the $\lambda$-return difficult in this context. In particular, off-policy methods that utilize experience replay remain problematic because their random sampling of minibatches is not conducive to the efficient calculation of $\lambda$-returns. Yet replay-based methods are often the most sample efficient, and incorporating $\lambda$-returns into them is a viable way to achieve new state-of-the-art performance. Towards this, we propose the first method to enable practical use of $\lambda$-returns in arbitrary replay-based methods without relying on other forms of decorrelation such as asynchronous gradient updates. By promoting short sequences of past transitions into a small cache within the replay memory, adjacent $\lambda$-returns can be efficiently precomputed by sharing Q-values. Computation is not wasted on experiences that are never sampled, and stored $\lambda$-returns behave as stable temporal-difference (TD) targets that replace the target network. Additionally, our method grants the unique ability to observe TD errors prior to sampling; for the first time, transitions can be prioritized by their true significance rather than by a proxy to it. Furthermore, we propose the novel use of the TD error to dynamically select $\lambda$-values that facilitate faster learning. We show that these innovations can enhance the performance of DQN when playing Atari 2600 games, even under partial observability. While our work specifically focuses on $\lambda$-returns, these ideas are applicable to any multi-step return estimator.
Tasks	Atari Games
Published	2018-10-23
URL	https://arxiv.org/abs/1810.09967v3
PDF	https://arxiv.org/pdf/1810.09967v3.pdf
PWC	https://paperswithcode.com/paper/efficient-eligibility-traces-for-deep
Repo	https://github.com/brett-daley/dqn-lambda
Framework	tf