July 28, 2019

3542 words 17 mins read

Paper Group ANR 311

A Brief Study of In-Domain Transfer and Learning from Fewer Samples using A Few Simple Priors. Camera Relocalization by Computing Pairwise Relative Poses Using Convolutional Neural Network. Synthesis of Near-regular Natural Textures. Towards Fully Environment-Aware UAVs: Real-Time Path Planning with Online 3D Wind Field Prediction in Complex Terrai …

A Brief Study of In-Domain Transfer and Learning from Fewer Samples using A Few Simple Priors


Title	A Brief Study of In-Domain Transfer and Learning from Fewer Samples using A Few Simple Priors
Authors	Marc Pickett, Ayush Sekhari, James Davidson
Abstract	Domain knowledge can often be encoded in the structure of a network, such as convolutional layers for vision, which has been shown to increase generalization and decrease sample complexity, or the number of samples required for successful learning. In this study, we ask whether sample complexity can be reduced for systems where the structure of the domain is unknown beforehand, and the structure and parameters must both be learned from the data. We show that sample complexity reduction through learning structure is possible for at least two simple cases. In studying these cases, we also gain insight into how this might be done for more complex domains.
Tasks
Published	2017-07-13
URL	http://arxiv.org/abs/1707.03979v1
PDF	http://arxiv.org/pdf/1707.03979v1.pdf
PWC	https://paperswithcode.com/paper/a-brief-study-of-in-domain-transfer-and
Repo
Framework

Camera Relocalization by Computing Pairwise Relative Poses Using Convolutional Neural Network


Title	Camera Relocalization by Computing Pairwise Relative Poses Using Convolutional Neural Network
Authors	Zakaria Laskar, Iaroslav Melekhov, Surya Kalia, Juho Kannala
Abstract	We propose a new deep learning based approach for camera relocalization. Our approach localizes a given query image by using a convolutional neural network (CNN) for first retrieving similar database images and then predicting the relative pose between the query and the database images, whose poses are known. The camera location for the query image is obtained via triangulation from two relative translation estimates using a RANSAC based approach. Each relative pose estimate provides a hypothesis for the camera orientation and they are fused in a second RANSAC scheme. The neural network is trained for relative pose estimation in an end-to-end manner using training image pairs. In contrast to previous work, our approach does not require scene-specific training of the network, which improves scalability, and it can also be applied to scenes which are not available during the training of the network. As another main contribution, we release a challenging indoor localisation dataset covering 5 different scenes registered to a common coordinate frame. We evaluate our approach using both our own dataset and the standard 7 Scenes benchmark. The results show that the proposed approach generalizes well to previously unseen scenes and compares favourably to other recent CNN-based methods.
Tasks	Camera Relocalization, Pose Estimation
Published	2017-07-31
URL	http://arxiv.org/abs/1707.09733v2
PDF	http://arxiv.org/pdf/1707.09733v2.pdf
PWC	https://paperswithcode.com/paper/camera-relocalization-by-computing-pairwise
Repo
Framework

Synthesis of Near-regular Natural Textures


Title	Synthesis of Near-regular Natural Textures
Authors	V. Asha
Abstract	Texture synthesis is widely used in the field of computer graphics, vision, and image processing. In the present paper, a texture synthesis algorithm is proposed for near-regular natural textures with the help of a representative periodic pattern extracted from the input textures using distance matching function. Local texture statistics is then analyzed against global texture statistics for non-overlapping windows of size same as periodic pattern size and a representative periodic pattern is extracted from the image and used for texture synthesis, while preserving the global regularity and visual appearance. Validation of the algorithm based on experiments with synthetic textures whose periodic pattern sizes are known and containing camouflages / defects proves the strength of the algorithm for texture synthesis and its application in detection of camouflages / defects in textures.
Tasks	Texture Synthesis
Published	2017-06-22
URL	http://arxiv.org/abs/1706.07198v1
PDF	http://arxiv.org/pdf/1706.07198v1.pdf
PWC	https://paperswithcode.com/paper/synthesis-of-near-regular-natural-textures
Repo
Framework

Towards Fully Environment-Aware UAVs: Real-Time Path Planning with Online 3D Wind Field Prediction in Complex Terrain


Title	Towards Fully Environment-Aware UAVs: Real-Time Path Planning with Online 3D Wind Field Prediction in Complex Terrain
Authors	Philipp Oettershagen, Florian Achermann, Benjamin Müller, Daniel Schneider, Roland Siegwart
Abstract	Today, low-altitude fixed-wing Unmanned Aerial Vehicles (UAVs) are largely limited to primitively follow user-defined waypoints. To allow fully-autonomous remote missions in complex environments, real-time environment-aware navigation is required both with respect to terrain and strong wind drafts. This paper presents two relevant initial contributions: First, the literature’s first-ever 3D wind field prediction method which can run in real time onboard a UAV is presented. The approach retrieves low-resolution global weather data, and uses potential flow theory to adjust the wind field such that terrain boundaries, mass conservation, and the atmospheric stratification are observed. A comparison with 1D LIDAR data shows an overall wind error reduction of 23% with respect to the zero-wind assumption that is mostly used for UAV path planning today. However, given that the vertical winds are not resolved accurately enough further research is required and identified. Second, a sampling-based path planner that considers the aircraft dynamics in non-uniform wind iteratively via Dubins airplane paths is presented. Performance optimizations, e.g. obstacle-aware sampling and fast 2.5D-map collision checks, render the planner 50% faster than the Open Motion Planning Library (OMPL) implementation. Test cases in Alpine terrain show that the wind-aware planning performs up to 50x less iterations than shortest-path planning and is thus slower in low winds, but that it tends to deliver lower-cost paths in stronger winds. More importantly, in contrast to the shortest-path planner, it always delivers collision-free paths. Overall, our initial research demonstrates the feasibility of 3D wind field prediction from a UAV and the advantages of wind-aware planning. This paves the way for follow-up research on fully-autonomous environment-aware navigation of UAVs in real-life missions and complex terrain.
Tasks	Motion Planning
Published	2017-12-10
URL	http://arxiv.org/abs/1712.03608v1
PDF	http://arxiv.org/pdf/1712.03608v1.pdf
PWC	https://paperswithcode.com/paper/towards-fully-environment-aware-uavs-real
Repo
Framework

On the Robustness of Convolutional Neural Networks to Internal Architecture and Weight Perturbations


Title	On the Robustness of Convolutional Neural Networks to Internal Architecture and Weight Perturbations
Authors	Nicholas Cheney, Martin Schrimpf, Gabriel Kreiman
Abstract	Deep convolutional neural networks are generally regarded as robust function approximators. So far, this intuition is based on perturbations to external stimuli such as the images to be classified. Here we explore the robustness of convolutional neural networks to perturbations to the internal weights and architecture of the network itself. We show that convolutional networks are surprisingly robust to a number of internal perturbations in the higher convolutional layers but the bottom convolutional layers are much more fragile. For instance, Alexnet shows less than a 30% decrease in classification performance when randomly removing over 70% of weight connections in the top convolutional or dense layers but performance is almost at chance with the same perturbation in the first convolutional layer. Finally, we suggest further investigations which could continue to inform the robustness of convolutional networks to internal perturbations.
Tasks
Published	2017-03-23
URL	http://arxiv.org/abs/1703.08245v1
PDF	http://arxiv.org/pdf/1703.08245v1.pdf
PWC	https://paperswithcode.com/paper/on-the-robustness-of-convolutional-neural
Repo
Framework

Analyzing the Weighted Nuclear Norm Minimization and Nuclear Norm Minimization based on Group Sparse Representation


Title	Analyzing the Weighted Nuclear Norm Minimization and Nuclear Norm Minimization based on Group Sparse Representation
Authors	Zhiyuan Zha, Xin Yuan, Bei Li, Xinggan Zhang, Xin Liu, Lan Tang, Ying-Chang Liang
Abstract	Rank minimization methods have attracted considerable interest in various areas, such as computer vision and machine learning. The most representative work is nuclear norm minimization (NNM), which can recover the matrix rank exactly under some restricted and theoretical guarantee conditions. However, for many real applications, NNM is not able to approximate the matrix rank accurately, since it often tends to over-shrink the rank components. To rectify the weakness of NNM, recent advances have shown that weighted nuclear norm minimization (WNNM) can achieve a better matrix rank approximation than NNM, which heuristically set the weight being inverse to the singular values. However, it still lacks a sound mathematical explanation on why WNNM is more feasible than NNM. In this paper, we propose a scheme to analyze WNNM and NNM from the perspective of the group sparse representation. Specifically, we design an adaptive dictionary to bridge the gap between the group sparse representation and the rank minimization models. Based on this scheme, we provide a mathematical derivation to explain why WNNM is more feasible than NNM. Moreover, due to the heuristical set of the weight, WNNM sometimes pops out error in the operation of SVD, and thus we present an adaptive weight setting scheme to avoid this error. We then employ the proposed scheme on two low-level vision tasks including image denoising and image inpainting. Experimental results demonstrate that WNNM is more feasible than NNM and the proposed scheme outperforms many current state-of-the-art methods.
Tasks	Denoising, Image Denoising, Image Inpainting
Published	2017-02-15
URL	http://arxiv.org/abs/1702.04463v5
PDF	http://arxiv.org/pdf/1702.04463v5.pdf
PWC	https://paperswithcode.com/paper/analyzing-the-weighted-nuclear-norm
Repo
Framework

Dialog Structure Through the Lens of Gender, Gender Environment, and Power


Title	Dialog Structure Through the Lens of Gender, Gender Environment, and Power
Authors	Vinodkumar Prabhakaran, Owen Rambow
Abstract	Understanding how the social context of an interaction affects our dialog behavior is of great interest to social scientists who study human behavior, as well as to computer scientists who build automatic methods to infer those social contexts. In this paper, we study the interaction of power, gender, and dialog behavior in organizational interactions. In order to perform this study, we first construct the Gender Identified Enron Corpus of emails, in which we semi-automatically assign the gender of around 23,000 individuals who authored around 97,000 email messages in the Enron corpus. This corpus, which is made freely available, is orders of magnitude larger than previously existing gender identified corpora in the email domain. Next, we use this corpus to perform a large-scale data-oriented study of the interplay of gender and manifestations of power. We argue that, in addition to one’s own gender, the “gender environment” of an interaction, i.e., the gender makeup of one’s interlocutors, also affects the way power is manifested in dialog. We focus especially on manifestations of power in the dialog structure — both, in a shallow sense that disregards the textual content of messages (e.g., how often do the participants contribute, how often do they get replies etc.), as well as the structure that is expressed within the textual content (e.g., who issues requests and how are they made, whose requests get responses etc.). We find that both gender and gender environment affect the ways power is manifested in dialog, resulting in patterns that reveal the underlying factors. Finally, we show the utility of gender information in the problem of automatically predicting the direction of power between pairs of participants in email interactions.
Tasks
Published	2017-06-12
URL	http://arxiv.org/abs/1706.03441v1
PDF	http://arxiv.org/pdf/1706.03441v1.pdf
PWC	https://paperswithcode.com/paper/dialog-structure-through-the-lens-of-gender
Repo
Framework

Efficient Localized Inference for Large Graphical Models


Title	Efficient Localized Inference for Large Graphical Models
Authors	Jinglin Chen, Jian Peng, Qiang Liu
Abstract	We propose a new localized inference algorithm for answering marginalization queries in large graphical models with the correlation decay property. Given a query variable and a large graphical model, we define a much smaller model in a local region around the query variable in the target model so that the marginal distribution of the query variable can be accurately approximated. We introduce two approximation error bounds based on the Dobrushin’s comparison theorem and apply our bounds to derive a greedy expansion algorithm that efficiently guides the selection of neighbor nodes for localized inference. We verify our theoretical bounds on various datasets and demonstrate that our localized inference algorithm can provide fast and accurate approximation for large graphical models.
Tasks
Published	2017-10-28
URL	http://arxiv.org/abs/1710.10404v1
PDF	http://arxiv.org/pdf/1710.10404v1.pdf
PWC	https://paperswithcode.com/paper/efficient-localized-inference-for-large
Repo
Framework

Finding Theme Communities from Database Networks


Title	Finding Theme Communities from Database Networks
Authors	Lingyang Chu, Zhefeng Wang, Jian Pei, Yanyan Zhang, Yu Yang, Enhong Chen
Abstract	Given a database network where each vertex is associated with a transaction database, we are interested in finding theme communities. Here, a theme community is a cohesive subgraph such that a common pattern is frequent in all transaction databases associated with the vertices in the subgraph. Finding all theme communities from a database network enjoys many novel applications. However, it is challenging since even counting the number of all theme communities in a database network is #P-hard. Inspired by the observation that a theme community shrinks when the length of the pattern increases, we investigate several properties of theme communities and develop TCFI, a scalable algorithm that uses these properties to effectively prune the patterns that cannot form any theme community. We also design TC-Tree, a scalable algorithm that decomposes and indexes theme communities efficiently. Retrieving a ranked list of theme communities from a TC-Tree of hundreds of millions of theme communities takes less than 1 second. Extensive experiments and a case study demonstrate the effectiveness and scalability of TCFI and TC-Tree in discovering and querying meaningful theme communities from large database networks.
Tasks
Published	2017-09-23
URL	https://arxiv.org/abs/1709.08083v2
PDF	https://arxiv.org/pdf/1709.08083v2.pdf
PWC	https://paperswithcode.com/paper/finding-theme-communities-from-database
Repo
Framework

Document Context Neural Machine Translation with Memory Networks


Title	Document Context Neural Machine Translation with Memory Networks
Authors	Sameen Maruf, Gholamreza Haffari
Abstract	We present a document-level neural machine translation model which takes both source and target document context into account using memory networks. We model the problem as a structured prediction problem with interdependencies among the observed and hidden variables, i.e., the source sentences and their unobserved target translations in the document. The resulting structured prediction problem is tackled with a neural translation model equipped with two memory components, one each for the source and target side, to capture the documental interdependencies. We train the model end-to-end, and propose an iterative decoding algorithm based on block coordinate descent. Experimental results of English translations from French, German, and Estonian documents show that our model is effective in exploiting both source and target document context, and statistically significantly outperforms the previous work in terms of BLEU and METEOR.
Tasks	Machine Translation, Structured Prediction
Published	2017-11-10
URL	http://arxiv.org/abs/1711.03688v2
PDF	http://arxiv.org/pdf/1711.03688v2.pdf
PWC	https://paperswithcode.com/paper/document-context-neural-machine-translation
Repo
Framework

A Data Driven Approach for Compound Figure Separation Using Convolutional Neural Networks


Title	A Data Driven Approach for Compound Figure Separation Using Convolutional Neural Networks
Authors	Satoshi Tsutsui, David Crandall
Abstract	A key problem in automatic analysis and understanding of scientific papers is to extract semantic information from non-textual paper components like figures, diagrams, tables, etc. Much of this work requires a very first preprocessing step: decomposing compound multi-part figures into individual subfigures. Previous work in compound figure separation has been based on manually designed features and separation rules, which often fail for less common figure types and layouts. Moreover, few implementations for compound figure decomposition are publicly available. This paper proposes a data driven approach to separate compound figures using modern deep Convolutional Neural Networks (CNNs) to train the separator in an end-to-end manner. CNNs eliminate the need for manually designing features and separation rules, but require a large amount of annotated training data. We overcome this challenge using transfer learning as well as automatically synthesizing training exemplars. We evaluate our technique on the ImageCLEF Medical dataset, achieving 85.9% accuracy and outperforming previous techniques. We have released our implementation as an easy-to-use Python library, aiming to promote further research in scientific figure mining.
Tasks	Transfer Learning
Published	2017-03-15
URL	http://arxiv.org/abs/1703.05105v2
PDF	http://arxiv.org/pdf/1703.05105v2.pdf
PWC	https://paperswithcode.com/paper/a-data-driven-approach-for-compound-figure
Repo
Framework

Routing Networks: Adaptive Selection of Non-linear Functions for Multi-Task Learning


Title	Routing Networks: Adaptive Selection of Non-linear Functions for Multi-Task Learning
Authors	Clemens Rosenbaum, Tim Klinger, Matthew Riemer
Abstract	Multi-task learning (MTL) with neural networks leverages commonalities in tasks to improve performance, but often suffers from task interference which reduces the benefits of transfer. To address this issue we introduce the routing network paradigm, a novel neural network and training algorithm. A routing network is a kind of self-organizing neural network consisting of two components: a router and a set of one or more function blocks. A function block may be any neural network - for example a fully-connected or a convolutional layer. Given an input the router makes a routing decision, choosing a function block to apply and passing the output back to the router recursively, terminating when a fixed recursion depth is reached. In this way the routing network dynamically composes different function blocks for each input. We employ a collaborative multi-agent reinforcement learning (MARL) approach to jointly train the router and function blocks. We evaluate our model against cross-stitch networks and shared-layer baselines on multi-task settings of the MNIST, mini-imagenet, and CIFAR-100 datasets. Our experiments demonstrate a significant improvement in accuracy, with sharper convergence. In addition, routing networks have nearly constant per-task training cost while cross-stitch networks scale linearly with the number of tasks. On CIFAR-100 (20 tasks) we obtain cross-stitch performance levels with an 85% reduction in training time.
Tasks	Multi-agent Reinforcement Learning, Multi-Task Learning
Published	2017-11-03
URL	http://arxiv.org/abs/1711.01239v2
PDF	http://arxiv.org/pdf/1711.01239v2.pdf
PWC	https://paperswithcode.com/paper/routing-networks-adaptive-selection-of-non
Repo
Framework

Prosocial learning agents solve generalized Stag Hunts better than selfish ones


Title	Prosocial learning agents solve generalized Stag Hunts better than selfish ones
Authors	Alexander Peysakhovich, Adam Lerer
Abstract	Deep reinforcement learning has become an important paradigm for constructing agents that can enter complex multi-agent situations and improve their policies through experience. One commonly used technique is reactive training - applying standard RL methods while treating other agents as a part of the learner’s environment. It is known that in general-sum games reactive training can lead groups of agents to converge to inefficient outcomes. We focus on one such class of environments: Stag Hunt games. Here agents either choose a risky cooperative policy (which leads to high payoffs if both choose it but low payoffs to an agent who attempts it alone) or a safe one (which leads to a safe payoff no matter what). We ask how we can change the learning rule of a single agent to improve its outcomes in Stag Hunts that include other reactive learners. We extend existing work on reward-shaping in multi-agent reinforcement learning and show that that making a single agent prosocial, that is, making them care about the rewards of their partners can increase the probability that groups converge to good outcomes. Thus, even if we control a single agent in a group making that agent prosocial can increase our agent’s long-run payoff. We show experimentally that this result carries over to a variety of more complex environments with Stag Hunt-like dynamics including ones where agents must learn from raw input pixels.
Tasks	Multi-agent Reinforcement Learning
Published	2017-09-08
URL	http://arxiv.org/abs/1709.02865v2
PDF	http://arxiv.org/pdf/1709.02865v2.pdf
PWC	https://paperswithcode.com/paper/prosocial-learning-agents-solve-generalized
Repo
Framework

Adversarial Transfer Learning for Cross-domain Visual Recognition


Title	Adversarial Transfer Learning for Cross-domain Visual Recognition
Authors	Shanshan Wang, Lei Zhang, JingRu Fu
Abstract	In many practical visual recognition scenarios, feature distribution in the source domain is generally different from that of the target domain, which results in the emergence of general cross-domain visual recognition problems. To address the problems of visual domain mismatch, we propose a novel semi-supervised adversarial transfer learning approach, which is called Coupled adversarial transfer Domain Adaptation (CatDA), for distribution alignment between two domains. The proposed CatDA approach is inspired by cycleGAN, but leveraging multiple shallow multilayer perceptrons (MLPs) instead of deep networks. Specifically, our CatDA comprises of two symmetric and slim sub-networks, such that the coupled adversarial learning framework is formulated. With such symmetry of two generators, the input data from source/target domain can be fed into the MLP network for target/source domain generation, supervised by two confrontation oriented coupled discriminators. Notably, in order to avoid the critical flaw of high-capacity of the feature extraction function during domain adversarial training, domain specific loss and domain knowledge fidelity loss are proposed in each generator, such that the effectiveness of the proposed transfer network is guaranteed. Additionally, the essential difference from cycleGAN is that our method aims to generate domain-agnostic and aligned features for domain adaptation and transfer learning rather than synthesize realistic images. We show experimentally on a number of benchmark datasets and the proposed approach achieves competitive performance over state-of-the-art domain adaptation and transfer learning approaches.
Tasks	Domain Adaptation, Transfer Learning
Published	2017-11-24
URL	https://arxiv.org/abs/1711.08904v2
PDF	https://arxiv.org/pdf/1711.08904v2.pdf
PWC	https://paperswithcode.com/paper/catgan-coupled-adversarial-transfer-for
Repo
Framework

Discrete Sequential Prediction of Continuous Actions for Deep RL


Title	Discrete Sequential Prediction of Continuous Actions for Deep RL
Authors	Luke Metz, Julian Ibarz, Navdeep Jaitly, James Davidson
Abstract	It has long been assumed that high dimensional continuous control problems cannot be solved effectively by discretizing individual dimensions of the action space due to the exponentially large number of bins over which policies would have to be learned. In this paper, we draw inspiration from the recent success of sequence-to-sequence models for structured prediction problems to develop policies over discretized spaces. Central to this method is the realization that complex functions over high dimensional spaces can be modeled by neural networks that predict one dimension at a time. Specifically, we show how Q-values and policies over continuous spaces can be modeled using a next step prediction model over discretized dimensions. With this parameterization, it is possible to both leverage the compositional structure of action spaces during learning, as well as compute maxima over action spaces (approximately). On a simple example task we demonstrate empirically that our method can perform global search, which effectively gets around the local optimization issues that plague DDPG. We apply the technique to off-policy (Q-learning) methods and show that our method can achieve the state-of-the-art for off-policy methods on several continuous control tasks.
Tasks	Continuous Control, Q-Learning, Structured Prediction
Published	2017-05-14
URL	https://arxiv.org/abs/1705.05035v3
PDF	https://arxiv.org/pdf/1705.05035v3.pdf
PWC	https://paperswithcode.com/paper/discrete-sequential-prediction-of-continuous
Repo
Framework