Paper Group ANR 1422
Robust and fast generation of top and side grasps for unknown objects. Exploration with Unreliable Intrinsic Reward in Multi-Agent Reinforcement Learning. Conflict Detection and Resolution in Table Top Scenarios for Human-Robot Interaction. A new operation mode for depth-focused high-sensitivity ToF range finding. Gabor Layers Enhance Network Robus …
Robust and fast generation of top and side grasps for unknown objects
| Title | Robust and fast generation of top and side grasps for unknown objects |
| Authors | Brice Denoun, Beatriz Leon, Claudio Zito, Rustam Stolkin, Lorenzo Jamone, Miles Hansard |
| Abstract | In this work, we present a geometry-based grasping algorithm that is capable of efficiently generating both top and side grasps for unknown objects, using a single view RGB-D camera, and of selecting the most promising one. We demonstrate the effectiveness of our approach on a picking scenario on a real robot platform. Our approach has shown to be more reliable than another recent geometry-based method considered as baseline [7] in terms of grasp stability, by increasing the successful grasp attempts by a factor of six. |
| Tasks | |
| Published | 2019-07-18 |
| URL | https://arxiv.org/abs/1907.08088v1 |
| https://arxiv.org/pdf/1907.08088v1.pdf | |
| PWC | https://paperswithcode.com/paper/robust-and-fast-generation-of-top-and-side |
| Repo | |
| Framework | |
Exploration with Unreliable Intrinsic Reward in Multi-Agent Reinforcement Learning
| Title | Exploration with Unreliable Intrinsic Reward in Multi-Agent Reinforcement Learning |
| Authors | Wendelin Böhmer, Tabish Rashid, Shimon Whiteson |
| Abstract | This paper investigates the use of intrinsic reward to guide exploration in multi-agent reinforcement learning. We discuss the challenges in applying intrinsic reward to multiple collaborative agents and demonstrate how unreliable reward can prevent decentralized agents from learning the optimal policy. We address this problem with a novel framework, Independent Centrally-assisted Q-learning (ICQL), in which decentralized agents share control and an experience replay buffer with a centralized agent. Only the centralized agent is intrinsically rewarded, but the decentralized agents still benefit from improved exploration, without the distraction of unreliable incentives. |
| Tasks | Multi-agent Reinforcement Learning, Q-Learning |
| Published | 2019-06-05 |
| URL | https://arxiv.org/abs/1906.02138v1 |
| https://arxiv.org/pdf/1906.02138v1.pdf | |
| PWC | https://paperswithcode.com/paper/exploration-with-unreliable-intrinsic-reward |
| Repo | |
| Framework | |
Conflict Detection and Resolution in Table Top Scenarios for Human-Robot Interaction
| Title | Conflict Detection and Resolution in Table Top Scenarios for Human-Robot Interaction |
| Authors | Avinash Kumar Singh, Kai-Florian Richter |
| Abstract | As in any interaction process, misunderstandings, ambiguity, and failures to correctly understand the interaction partner are bound to happen in human-robot interaction. We term these failures ‘conflicts’ and are interested in both conflict detection and conflict resolution. In that, we focus on the robot’s perspective. For the robot, conflicts may occur because of errors in its perceptual processes or because of ambiguity stemming from human input. This poster presents a brief system overview, and details Here, we briefly outline the project’s motivation and setting, introduce the general processing framework, and then present two kinds of conflicts in some more detail: 1) a failure to identify a relevant object at all; 2) ambiguity emerging from multiple matches in scene perception. |
| Tasks | |
| Published | 2019-12-16 |
| URL | https://arxiv.org/abs/1912.08097v2 |
| https://arxiv.org/pdf/1912.08097v2.pdf | |
| PWC | https://paperswithcode.com/paper/conflict-detection-and-resolution-in-table |
| Repo | |
| Framework | |
A new operation mode for depth-focused high-sensitivity ToF range finding
| Title | A new operation mode for depth-focused high-sensitivity ToF range finding |
| Authors | Sebastian Werner, Henrik Schäfer, Matthias Hullin |
| Abstract | We introduce pulsed correlation time-of-flight (PC-ToF) sensing, a new operation mode for correlation time-of-flight range sensors that combines a sub-nanosecond laser pulse source with a rectangular demodulation at the sensor side. In contrast to previous work, our proposed measurement scheme attempts not to optimize depth accuracy over the full measurement: With PC-ToF we trade the global sensitivity of a standard C-ToF setup for measurements with strongly localized high sensitivity – we greatly enhance the depth resolution for the acquisition of scene features around a desired depth of interest. Using real-world experiments, we show that our technique is capable of achieving depth resolutions down to 2mm using a modulation frequency as low as 10MHz and an optical power as low as 1mW. This makes PC-ToF especially viable for low-power applications. |
| Tasks | |
| Published | 2019-09-06 |
| URL | https://arxiv.org/abs/1909.02759v1 |
| https://arxiv.org/pdf/1909.02759v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-new-operation-mode-for-depth-focused-high |
| Repo | |
| Framework | |
Gabor Layers Enhance Network Robustness
| Title | Gabor Layers Enhance Network Robustness |
| Authors | Juan C. Pérez, Motasem Alfarra, Guillaume Jeanneret, Adel Bibi, Ali Thabet, Bernard Ghanem, Pablo Arbeláez |
| Abstract | We revisit the benefits of merging classical vision concepts with deep learning models. In particular, we explore the effect on robustness against adversarial attacks of replacing the first layers of various deep architectures with Gabor layers, i.e. convolutional layers with filters that are based on learnable Gabor parameters. We observe that architectures enhanced with Gabor layers gain a consistent boost in robustness over regular models and preserve high generalizing test performance, even though these layers come at a negligible increase in the number of parameters. We then exploit the closed form expression of Gabor filters to derive an expression for a Lipschitz constant of such filters, and harness this theoretical result to develop a regularizer we use during training to further enhance network robustness. We conduct extensive experiments with various architectures (LeNet, AlexNet, VGG16 and WideResNet) on several datasets (MNIST, SVHN, CIFAR10 and CIFAR100) and demonstrate large empirical robustness gains. Furthermore, we experimentally show how our regularizer provides consistent robustness improvements. |
| Tasks | |
| Published | 2019-12-11 |
| URL | https://arxiv.org/abs/1912.05661v2 |
| https://arxiv.org/pdf/1912.05661v2.pdf | |
| PWC | https://paperswithcode.com/paper/robust-gabor-networks |
| Repo | |
| Framework | |
Wasserstein-Wasserstein Auto-Encoders
| Title | Wasserstein-Wasserstein Auto-Encoders |
| Authors | Shunkang Zhang, Yuan Gao, Yuling Jiao, Jin Liu, Yang Wang, Can Yang |
| Abstract | To address the challenges in learning deep generative models (e.g.,the blurriness of variational auto-encoder and the instability of training generative adversarial networks, we propose a novel deep generative model, named Wasserstein-Wasserstein auto-encoders (WWAE). We formulate WWAE as minimization of the penalized optimal transport between the target distribution and the generated distribution. By noticing that both the prior $P_Z$ and the aggregated posterior $Q_Z$ of the latent code Z can be well captured by Gaussians, the proposed WWAE utilizes the closed-form of the squared Wasserstein-2 distance for two Gaussians in the optimization process. As a result, WWAE does not suffer from the sampling burden and it is computationally efficient by leveraging the reparameterization trick. Numerical results evaluated on multiple benchmark datasets including MNIST, fashion- MNIST and CelebA show that WWAE learns better latent structures than VAEs and generates samples of better visual quality and higher FID scores than VAEs and GANs. |
| Tasks | |
| Published | 2019-02-25 |
| URL | http://arxiv.org/abs/1902.09323v1 |
| http://arxiv.org/pdf/1902.09323v1.pdf | |
| PWC | https://paperswithcode.com/paper/wasserstein-wasserstein-auto-encoders |
| Repo | |
| Framework | |
Learning Task Relatedness in Multi-Task Learning for Images in Context
| Title | Learning Task Relatedness in Multi-Task Learning for Images in Context |
| Authors | Gjorgji Strezoski, Nanne van Noord, Marcel Worring |
| Abstract | Multimedia applications often require concurrent solutions to multiple tasks. These tasks hold clues to each-others solutions, however as these relations can be complex this remains a rarely utilized property. When task relations are explicitly defined based on domain knowledge multi-task learning (MTL) offers such concurrent solutions, while exploiting relatedness between multiple tasks performed over the same dataset. In most cases however, this relatedness is not explicitly defined and the domain expert knowledge that defines it is not available. To address this issue, we introduce Selective Sharing, a method that learns the inter-task relatedness from secondary latent features while the model trains. Using this insight, we can automatically group tasks and allow them to share knowledge in a mutually beneficial way. We support our method with experiments on 5 datasets in classification, regression, and ranking tasks and compare to strong baselines and state-of-the-art approaches showing a consistent improvement in terms of accuracy and parameter counts. In addition, we perform an activation region analysis showing how Selective Sharing affects the learned representation. |
| Tasks | Multi-Task Learning |
| Published | 2019-04-05 |
| URL | http://arxiv.org/abs/1904.03011v1 |
| http://arxiv.org/pdf/1904.03011v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-task-relatedness-in-multi-task |
| Repo | |
| Framework | |
Adapting Behaviour via Intrinsic Reward: A Survey and Empirical Study
| Title | Adapting Behaviour via Intrinsic Reward: A Survey and Empirical Study |
| Authors | Cam Linke, Nadia M. Ady, Martha White, Thomas Degris, Adam White |
| Abstract | Learning about many things can provide numerous benefits to a reinforcement learning system. For example, learning many auxiliary value functions, in addition to optimizing the environmental reward, appears to improve both exploration and representation learning. The question we tackle in this paper is how to sculpt the stream of experience—how to adapt the system’s behaviour—to optimize the learning of a collection of value functions. A simple answer is to compute an intrinsic reward based on the statistics of each auxiliary learner, and use reinforcement learning to maximize that intrinsic reward. Unfortunately, implementing this simple idea has proven difficult, and thus has been the focus of decades of study. It remains unclear which of the many possible measures of learning would work well in a parallel learning setting where environmental reward is extremely sparse or absent. In this paper, we investigate and compare different intrinsic reward mechanisms in a new bandit-like parallel-learning testbed. We discuss the interaction between reward and prediction learners and highlight the importance of introspective prediction learners: those that increase their rate of learning when progress is possible, and decrease when it is not. We provide a comprehensive empirical comparison of 15 different rewards, including well-known ideas from reinforcement learning and active learning. Our results highlight a simple but seemingly powerful principle: intrinsic rewards based on the amount of learning can generate useful behaviour, if each individual learner is introspective. |
| Tasks | Active Learning, Representation Learning |
| Published | 2019-06-19 |
| URL | https://arxiv.org/abs/1906.07865v1 |
| https://arxiv.org/pdf/1906.07865v1.pdf | |
| PWC | https://paperswithcode.com/paper/adapting-behaviour-via-intrinsic-reward-a |
| Repo | |
| Framework | |
Particle Swarm and EDAs
| Title | Particle Swarm and EDAs |
| Authors | Alison Jenkins, Vinika Gupta, Alexis Myrick, Mary Lenoir |
| Abstract | The Particle Swarm Optimization (PSO) algorithm is developed for solving the Schaffer F6 function in fewer than 4000 function evaluations on a total of 30 runs. Four variations of the Full Model of Particle Swarm Optimization (PSO) algorithms are presented which consist of combinations of Ring and Star topologies with Synchronous and Asynchronous updates. The Full Model with combinations of Ring and Star topologies in combination with Synchronous and Asynchronous Particle Updates is explored. |
| Tasks | |
| Published | 2019-11-16 |
| URL | https://arxiv.org/abs/1911.07112v1 |
| https://arxiv.org/pdf/1911.07112v1.pdf | |
| PWC | https://paperswithcode.com/paper/particle-swarm-and-edas |
| Repo | |
| Framework | |
On the Learning Dynamics of Two-layer Nonlinear Convolutional Neural Networks
| Title | On the Learning Dynamics of Two-layer Nonlinear Convolutional Neural Networks |
| Authors | Bing Yu, Junzhao Zhang, Zhanxing Zhu |
| Abstract | Convolutional neural networks (CNNs) have achieved remarkable performance in various fields, particularly in the domain of computer vision. However, why this architecture works well remains to be a mystery. In this work we move a small step toward understanding the success of CNNs by investigating the learning dynamics of a two-layer nonlinear convolutional neural network over some specific data distributions. Rather than the typical Gaussian assumption for input data distribution, we consider a more realistic setting that each data point (e.g. image) contains a specific pattern determining its class label. Within this setting, we both theoretically and empirically show that some convolutional filters will learn the key patterns in data and the norm of these filters will dominate during the training process with stochastic gradient descent. And with any high probability, when the number of iterations is sufficiently large, the CNN model could obtain 100% accuracy over the considered data distributions. Our experiments demonstrate that for practical image classification tasks our findings still hold to some extent. |
| Tasks | Image Classification |
| Published | 2019-05-24 |
| URL | https://arxiv.org/abs/1905.10157v1 |
| https://arxiv.org/pdf/1905.10157v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-learning-dynamics-of-two-layer |
| Repo | |
| Framework | |
Generative Grading: Neural Approximate Parsing for Automated Student Feedback
| Title | Generative Grading: Neural Approximate Parsing for Automated Student Feedback |
| Authors | Ali Malik, Mike Wu, Vrinda Vasavada, Jinpeng Song, John Mitchell, Noah Goodman, Chris Piech |
| Abstract | Open access to high-quality education is limited by the difficulty of providing student feedback. In this paper, we present Generative Grading with Neural Approximate Parsing (GG-NAP): a novel computational approach for providing feedback at scale that is capable of both accurately grading student work while also providing verifiability–a property where the model is able to substantiate its claims with a provable certificate. Our approach uses generative descriptions of student cognition, written as probabilistic programs, to synthesise millions of labelled example solutions to a problem; it then trains inference networks to approximately parse real student solutions according to these generative models. We achieve feedback prediction accuracy comparable to professional human experts in a variety of settings: short-answer questions, programs with graphical output, block-based programming, and short Java programs. In a real classroom, we ran an experiment where humans used GG-NAP to grade, yielding doubled grading accuracy while halving grading time. |
| Tasks | |
| Published | 2019-05-23 |
| URL | https://arxiv.org/abs/1905.09916v2 |
| https://arxiv.org/pdf/1905.09916v2.pdf | |
| PWC | https://paperswithcode.com/paper/generative-grading-neural-approximate-parsing |
| Repo | |
| Framework | |
Study of dynamical system based obstacle avoidance via manipulating orthogonal coordinates
| Title | Study of dynamical system based obstacle avoidance via manipulating orthogonal coordinates |
| Authors | Weiya Ren |
| Abstract | In this paper, we consider the general problem of obstacle avoidance based on dynamical system. The modulation matrix is developed by introducing orthogonal coordinates, which makes the modulation matrix more reasonable. The new trajectory’s direction can be represented by the linear combination of orthogonal coordinates. A orthogonal coordinates manipulating approach is proposed by introducing rotating matrix to solve the local minimal problem and provide more reasonable motions in 3-D or higher dimension space. The proposed method also provide a solution for patrolling around a convex shape. Experimental results on several designed dynamical systems demonstrate the effectiveness of the proposed approach. |
| Tasks | |
| Published | 2019-02-14 |
| URL | http://arxiv.org/abs/1902.05343v2 |
| http://arxiv.org/pdf/1902.05343v2.pdf | |
| PWC | https://paperswithcode.com/paper/study-of-dynamical-system-based-obstacle |
| Repo | |
| Framework | |
GraphX$^{NET}-$ Chest X-Ray Classification Under Extreme Minimal Supervision
| Title | GraphX$^{NET}-$ Chest X-Ray Classification Under Extreme Minimal Supervision |
| Authors | Angelica I. Aviles-Rivero, Nicolas Papadakis, Ruoteng Li, Philip Sellars, Qingnan Fan, Robby T. Tan, Carola-Bibiane Schönlieb |
| Abstract | The task of classifying X-ray data is a problem of both theoretical and clinical interest. Whilst supervised deep learning methods rely upon huge amounts of labelled data, the critical problem of achieving a good classification accuracy when an extremely small amount of labelled data is available has yet to be tackled. In this work, we introduce a novel semi-supervised framework for X-ray classification which is based on a graph-based optimisation model. To the best of our knowledge, this is the first method that exploits graph-based semi-supervised learning for X-ray data classification. Furthermore, we introduce a new multi-class classification functional with carefully selected class priors which allows for a smooth solution that strengthens the synergy between the limited number of labels and the huge amount of unlabelled data. We demonstrate, through a set of numerical and visual experiments, that our method produces highly competitive results on the ChestX-ray14 data set whilst drastically reducing the need for annotated data. |
| Tasks | |
| Published | 2019-07-23 |
| URL | https://arxiv.org/abs/1907.10085v2 |
| https://arxiv.org/pdf/1907.10085v2.pdf | |
| PWC | https://paperswithcode.com/paper/graphxnet-chest-x-ray-classification-under |
| Repo | |
| Framework | |
Addressing Limited Weight Resolution in a Fully Optical Neuromorphic Reservoir Computing Readout
| Title | Addressing Limited Weight Resolution in a Fully Optical Neuromorphic Reservoir Computing Readout |
| Authors | Chonghuai Ma, Floris Laporte, Joni Dambre, Peter Bienstman |
| Abstract | Using optical hardware for neuromorphic computing has become more and more popular recently due to its efficient high-speed data processing capabilities and low power consumption. However, there are still some remaining obstacles to realizing the vision of a completely optical neuromorphic computer. One of them is that, depending on the technology used, optical weighting elements may not share the same resolution as in the electrical domain. Moreover, noise and drift are important considerations as well. In this article, we investigate a new method for improving the performance of optical weighting, even in the presence of noise and in the case of very low resolution. Even with only 8 to 32 levels of resolution, the method can outperform the naive traditional low-resolution weighting by several orders of magnitude in terms of bit error rate and can deliver performance very close to full-resolution weighting elements, also in noisy environments. |
| Tasks | |
| Published | 2019-06-06 |
| URL | https://arxiv.org/abs/1908.02728v1 |
| https://arxiv.org/pdf/1908.02728v1.pdf | |
| PWC | https://paperswithcode.com/paper/addressing-limited-weight-resolution-in-a |
| Repo | |
| Framework | |
Leveraging Structural and Semantic Correspondence for Attribute-Oriented Aspect Sentiment Discovery
| Title | Leveraging Structural and Semantic Correspondence for Attribute-Oriented Aspect Sentiment Discovery |
| Authors | Zhe Zhang, Munindar P. Singh |
| Abstract | Opinionated text often involves attributes such as authorship and location that influence the sentiments expressed for different aspects. We posit that structural and semantic correspondence is both prevalent in opinionated text, especially when associated with attributes, and crucial in accurately revealing its latent aspect and sentiment structure. However, it is not recognized by existing approaches. We propose Trait, an unsupervised probabilistic model that discovers aspects and sentiments from text and associates them with different attributes. To this end, Trait infers and leverages structural and semantic correspondence using a Markov Random Field. We show empirically that by incorporating attributes explicitly Trait significantly outperforms state-of-the-art baselines both by generating attribute profiles that accord with our intuitions, as shown via visualization, and yielding topics of greater semantic cohesion. |
| Tasks | |
| Published | 2019-08-28 |
| URL | https://arxiv.org/abs/1908.10970v1 |
| https://arxiv.org/pdf/1908.10970v1.pdf | |
| PWC | https://paperswithcode.com/paper/leveraging-structural-and-semantic |
| Repo | |
| Framework | |
