Paper Group ANR 1363
Towards hardware acceleration for parton densities estimation. Fast Adaptation with Meta-Reinforcement Learning for Trust Modelling in Human-Robot Interaction. Robust Deep Sensing Through Transfer Learning in Cognitive Radio. Error Analysis of Elitist Random Search Heuristics. ZK-GanDef: A GAN based Zero Knowledge Adversarial Training Defense for N …
Towards hardware acceleration for parton densities estimation
| Title | Towards hardware acceleration for parton densities estimation |
| Authors | Stefano Carrazza, Juan Cruz-Martinez, Jesús Urtasun-Elizari, Emilio Villa |
| Abstract | In this proceedings we describe the computational challenges associated to the determination of parton distribution functions (PDFs). We compare the performance of the convolution of the parton distributions with matrix elements using different hardware instructions. We quantify and identify the most promising data-model configurations to increase PDF fitting performance in adapting the current code frameworks to hardware accelerators such as graphics processing units. |
| Tasks | |
| Published | 2019-09-23 |
| URL | https://arxiv.org/abs/1909.10547v1 |
| https://arxiv.org/pdf/1909.10547v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-hardware-acceleration-for-parton |
| Repo | |
| Framework | |
Fast Adaptation with Meta-Reinforcement Learning for Trust Modelling in Human-Robot Interaction
| Title | Fast Adaptation with Meta-Reinforcement Learning for Trust Modelling in Human-Robot Interaction |
| Authors | Yuan Gao, Elena Sibirtseva, Ginevra Castellano, Danica Kragic |
| Abstract | In socially assistive robotics, an important research area is the development of adaptation techniques and their effect on human-robot interaction. We present a meta-learning based policy gradient method for addressing the problem of adaptation in human-robot interaction and also investigate its role as a mechanism for trust modelling. By building an escape room scenario in mixed reality with a robot, we test our hypothesis that bi-directional trust can be influenced by different adaptation algorithms. We found that our proposed model increased the perceived trustworthiness of the robot and influenced the dynamics of gaining human’s trust. Additionally, participants evaluated that the robot perceived them as more trustworthy during the interactions with the meta-learning based adaptation compared to the previously studied statistical adaptation model. |
| Tasks | Meta-Learning |
| Published | 2019-08-12 |
| URL | https://arxiv.org/abs/1908.04087v1 |
| https://arxiv.org/pdf/1908.04087v1.pdf | |
| PWC | https://paperswithcode.com/paper/fast-adaptation-with-meta-reinforcement |
| Repo | |
| Framework | |
Robust Deep Sensing Through Transfer Learning in Cognitive Radio
| Title | Robust Deep Sensing Through Transfer Learning in Cognitive Radio |
| Authors | Qihang Peng, Andrew Gilman, Nuno Vasconcelos, Pamela C. Cosman, Laurence B. Milstein |
| Abstract | We propose a robust spectrum sensing framework based on deep learning. The received signals at the secondary user’s receiver are filtered, sampled and then directly fed into a convolutional neural network. Although this deep sensing is effective when operating in the same scenario as the collected training data, the sensing performance is degraded when it is applied in a different scenario with different wireless signals and propagation. We incorporate transfer learning into the framework to improve the robustness. Results validate the effectiveness as well as the robustness of the proposed deep spectrum sensing framework. |
| Tasks | Transfer Learning |
| Published | 2019-08-01 |
| URL | https://arxiv.org/abs/1908.00658v1 |
| https://arxiv.org/pdf/1908.00658v1.pdf | |
| PWC | https://paperswithcode.com/paper/robust-deep-sensing-through-transfer-learning |
| Repo | |
| Framework | |
Error Analysis of Elitist Random Search Heuristics
| Title | Error Analysis of Elitist Random Search Heuristics |
| Authors | Yu Chen, Cong Wang, Jun He, Chengwang Xie |
| Abstract | When random search heuristics (RSH) cannot locate precise globally optimal solutions with satisfactory performances, hitting time/running time analysis method is not flexible enough to accommodate the requirement of theoretical performance study. Thus, an alternative routine is needed to bridge the gap between theoretical analysis and algorithm implementation. Inspired by this idea, this paper is dedicated to perform an error analysis for elitist RSHs. By diagonalizing the transition matrix of a Markov chain model, the $t$-step transition matrix can be computed for any iteration budget $t$. Then, A general framework for estimation of expected approximation errors can be proposed. Case studies indicate that the error analysis works well for both uni- and multi-modal benchmark problems. It leads to precise estimations of approximation error instead of asymptotic results on fitness values, which demonstrates its competitiveness to fixed budget analysis. |
| Tasks | |
| Published | 2019-09-03 |
| URL | https://arxiv.org/abs/1909.00894v3 |
| https://arxiv.org/pdf/1909.00894v3.pdf | |
| PWC | https://paperswithcode.com/paper/estimating-approximation-errors-of-elitist |
| Repo | |
| Framework | |
ZK-GanDef: A GAN based Zero Knowledge Adversarial Training Defense for Neural Networks
| Title | ZK-GanDef: A GAN based Zero Knowledge Adversarial Training Defense for Neural Networks |
| Authors | Guanxiong Liu, Issa Khalil, Abdallah Khreishah |
| Abstract | Neural Network classifiers have been used successfully in a wide range of applications. However, their underlying assumption of attack free environment has been defied by adversarial examples. Researchers tried to develop defenses; however, existing approaches are still far from providing effective solutions to this evolving problem. In this paper, we design a generative adversarial net (GAN) based zero knowledge adversarial training defense, dubbed ZK-GanDef, which does not consume adversarial examples during training. Therefore, ZK-GanDef is not only efficient in training but also adaptive to new adversarial examples. This advantage comes at the cost of small degradation in test accuracy compared to full knowledge approaches. Our experiments show that ZK-GanDef enhances test accuracy on adversarial examples by up-to 49.17% compared to zero knowledge approaches. More importantly, its test accuracy is close to that of the state-of-the-art full knowledge approaches (maximum degradation of 8.46%), while taking much less training time. |
| Tasks | |
| Published | 2019-04-17 |
| URL | http://arxiv.org/abs/1904.08516v1 |
| http://arxiv.org/pdf/1904.08516v1.pdf | |
| PWC | https://paperswithcode.com/paper/zk-gandef-a-gan-based-zero-knowledge |
| Repo | |
| Framework | |
Planning in Hierarchical Reinforcement Learning: Guarantees for Using Local Policies
| Title | Planning in Hierarchical Reinforcement Learning: Guarantees for Using Local Policies |
| Authors | Tom Zahavy, Avinatan Hasidim, Haim Kaplan, Yishay Mansour |
| Abstract | We consider a settings of hierarchical reinforcement learning, in which the reward is a sum of components. For each component we are given a policy that maximizes it and our goal is to assemble a policy from the individual policies that maximizes the sum of the components. We provide theoretical guarantees for assembling such policies in deterministic MDPs with collectible rewards. Our approach builds on formulating this problem as a traveling salesman problem with discounted reward. We focus on local solutions, i.e., policies that only use information from the current state; thus, they are easy to implement and do not require substantial computational resources. We propose three local stochastic policies and prove that they guarantee better performance than any deterministic local policy in the worst case; experimental results suggest that they also perform better on average. |
| Tasks | Hierarchical Reinforcement Learning |
| Published | 2019-02-26 |
| URL | https://arxiv.org/abs/1902.10140v2 |
| https://arxiv.org/pdf/1902.10140v2.pdf | |
| PWC | https://paperswithcode.com/paper/planning-in-hierarchical-reinforcement |
| Repo | |
| Framework | |
BIGPATENT: A Large-Scale Dataset for Abstractive and Coherent Summarization
| Title | BIGPATENT: A Large-Scale Dataset for Abstractive and Coherent Summarization |
| Authors | Eva Sharma, Chen Li, Lu Wang |
| Abstract | Most existing text summarization datasets are compiled from the news domain, where summaries have a flattened discourse structure. In such datasets, summary-worthy content often appears in the beginning of input articles. Moreover, large segments from input articles are present verbatim in their respective summaries. These issues impede the learning and evaluation of systems that can understand an article’s global content structure as well as produce abstractive summaries with high compression ratio. In this work, we present a novel dataset, BIGPATENT, consisting of 1.3 million records of U.S. patent documents along with human written abstractive summaries. Compared to existing summarization datasets, BIGPATENT has the following properties: i) summaries contain a richer discourse structure with more recurring entities, ii) salient content is evenly distributed in the input, and iii) lesser and shorter extractive fragments are present in the summaries. Finally, we train and evaluate baselines and popular learning models on BIGPATENT to shed light on new challenges and motivate future directions for summarization research. |
| Tasks | Text Summarization |
| Published | 2019-06-10 |
| URL | https://arxiv.org/abs/1906.03741v1 |
| https://arxiv.org/pdf/1906.03741v1.pdf | |
| PWC | https://paperswithcode.com/paper/bigpatent-a-large-scale-dataset-for |
| Repo | |
| Framework | |
Scalable Gaussian Process Classification with Additive Noise for Various Likelihoods
| Title | Scalable Gaussian Process Classification with Additive Noise for Various Likelihoods |
| Authors | Haitao Liu, Yew-Soon Ong, Ziwei Yu, Jianfei Cai, Xiaobo Shen |
| Abstract | Gaussian process classification (GPC) provides a flexible and powerful statistical framework describing joint distributions over function space. Conventional GPCs however suffer from (i) poor scalability for big data due to the full kernel matrix, and (ii) intractable inference due to the non-Gaussian likelihoods. Hence, various scalable GPCs have been proposed through (i) the sparse approximation built upon a small inducing set to reduce the time complexity; and (ii) the approximate inference to derive analytical evidence lower bound (ELBO). However, these scalable GPCs equipped with analytical ELBO are limited to specific likelihoods or additional assumptions. In this work, we present a unifying framework which accommodates scalable GPCs using various likelihoods. Analogous to GP regression (GPR), we introduce additive noises to augment the probability space for (i) the GPCs with step, (multinomial) probit and logit likelihoods via the internal variables; and particularly, (ii) the GPC using softmax likelihood via the noise variables themselves. This leads to unified scalable GPCs with analytical ELBO by using variational inference. Empirically, our GPCs showcase better results than state-of-the-art scalable GPCs for extensive binary/multi-class classification tasks with up to two million data points. |
| Tasks | |
| Published | 2019-09-14 |
| URL | https://arxiv.org/abs/1909.06541v1 |
| https://arxiv.org/pdf/1909.06541v1.pdf | |
| PWC | https://paperswithcode.com/paper/scalable-gaussian-process-classification-with |
| Repo | |
| Framework | |
Multi-modal Active Learning From Human Data: A Deep Reinforcement Learning Approach
| Title | Multi-modal Active Learning From Human Data: A Deep Reinforcement Learning Approach |
| Authors | Ognjen Rudovic, Meiru Zhang, Bjorn Schuller, Rosalind W. Picard |
| Abstract | Human behavior expression and experience are inherently multi-modal, and characterized by vast individual and contextual heterogeneity. To achieve meaningful human-computer and human-robot interactions, multi-modal models of the users states (e.g., engagement) are therefore needed. Most of the existing works that try to build classifiers for the users states assume that the data to train the models are fully labeled. Nevertheless, data labeling is costly and tedious, and also prone to subjective interpretations by the human coders. This is even more pronounced when the data are multi-modal (e.g., some users are more expressive with their facial expressions, some with their voice). Thus, building models that can accurately estimate the users states during an interaction is challenging. To tackle this, we propose a novel multi-modal active learning (AL) approach that uses the notion of deep reinforcement learning (RL) to find an optimal policy for active selection of the users data, needed to train the target (modality-specific) models. We investigate different strategies for multi-modal data fusion, and show that the proposed model-level fusion coupled with RL outperforms the feature-level and modality-specific models, and the naive AL strategies such as random sampling, and the standard heuristics such as uncertainty sampling. We show the benefits of this approach on the task of engagement estimation from real-world child-robot interactions during an autism therapy. Importantly, we show that the proposed multi-modal AL approach can be used to efficiently personalize the engagement classifiers to the target user using a small amount of actively selected users data. |
| Tasks | Active Learning |
| Published | 2019-06-07 |
| URL | https://arxiv.org/abs/1906.03098v1 |
| https://arxiv.org/pdf/1906.03098v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-modal-active-learning-from-human-data-a |
| Repo | |
| Framework | |
Unsupervised Segmentation of Fire and Smoke from Infra-Red Videos
| Title | Unsupervised Segmentation of Fire and Smoke from Infra-Red Videos |
| Authors | Meenu Ajith, Manel Martínez-Ramón |
| Abstract | This paper proposes a vision-based fire and smoke segmentation system which use spatial, temporal and motion information to extract the desired regions from the video frames. The fusion of information is done using multiple features such as optical flow, divergence and intensity values. These features extracted from the images are used to segment the pixels into different classes in an unsupervised way. A comparative analysis is done by using multiple clustering algorithms for segmentation. Here the Markov Random Field performs more accurately than other segmentation algorithms since it characterizes the spatial interactions of pixels using a finite number of parameters. It builds a probabilistic image model that selects the most likely labeling using the maximum a posteriori (MAP) estimation. This unsupervised approach is tested on various images and achieves a frame-wise fire detection rate of 95.39%. Hence this method can be used for early detection of fire in real-time and it can be incorporated into an indoor or outdoor surveillance system. |
| Tasks | Optical Flow Estimation |
| Published | 2019-09-18 |
| URL | https://arxiv.org/abs/1909.12937v1 |
| https://arxiv.org/pdf/1909.12937v1.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-segmentation-of-fire-and-smoke |
| Repo | |
| Framework | |
Fuzzy Rule Interpolation Toolbox for the GNU Open-Source OCTAVE
| Title | Fuzzy Rule Interpolation Toolbox for the GNU Open-Source OCTAVE |
| Authors | Maen Alzubi, Mohammad Almseidin, Mohd Aaqib Lone, Szilveszter Kovacs |
| Abstract | In most fuzzy control applications (applying classical fuzzy reasoning), the reasoning method requires a complete fuzzy rule-base, i.e all the possible observations must be covered by the antecedents of the fuzzy rules, which is not always available. Fuzzy control systems based on the Fuzzy Rule Interpolation (FRI) concept play a major role in different platforms, in case if only a sparse fuzzy rule-base is available. This cases the fuzzy model contains only the most relevant rules, without covering all the antecedent universes. The first FRI toolbox being able to handle different FRI methods was developed by Johanyak et. al. in 2006 for the MATLAB environment. The goal of this paper is to introduce some details of the adaptation of the FRI toolbox to support the GNU/OCTAVE programming language. The OCTAVE Fuzzy Rule Interpolation (OCTFRI) Toolbox is an open-source toolbox for OCTAVE programming language, providing a large functionally compatible subset of the MATLAB FRI toolbox as well as many extensions. The OCTFRI Toolbox includes functions that enable the user to evaluate Fuzzy Inference Systems (FISs) from the command line and from OCTAVE scripts, read/write FISs and OBS to/from files, and produce a graphical visualisation of both the membership functions and the FIS outputs. Future work will focus on implementing advanced fuzzy inference techniques and GUI tools. |
| Tasks | |
| Published | 2019-12-10 |
| URL | https://arxiv.org/abs/1912.04999v1 |
| https://arxiv.org/pdf/1912.04999v1.pdf | |
| PWC | https://paperswithcode.com/paper/fuzzy-rule-interpolation-toolbox-for-the-gnu |
| Repo | |
| Framework | |
An Internal Learning Approach to Video Inpainting
| Title | An Internal Learning Approach to Video Inpainting |
| Authors | Haotian Zhang, Long Mai, Ning Xu, Zhaowen Wang, John Collomosse, Hailin Jin |
| Abstract | We propose a novel video inpainting algorithm that simultaneously hallucinates missing appearance and motion (optical flow) information, building upon the recent ‘Deep Image Prior’ (DIP) that exploits convolutional network architectures to enforce plausible texture in static images. In extending DIP to video we make two important contributions. First, we show that coherent video inpainting is possible without a priori training. We take a generative approach to inpainting based on internal (within-video) learning without reliance upon an external corpus of visual data to train a one-size-fits-all model for the large space of general videos. Second, we show that such a framework can jointly generate both appearance and flow, whilst exploiting these complementary modalities to ensure mutual consistency. We show that leveraging appearance statistics specific to each video achieves visually plausible results whilst handling the challenging problem of long-term consistency. |
| Tasks | Optical Flow Estimation, Video Inpainting |
| Published | 2019-09-17 |
| URL | https://arxiv.org/abs/1909.07957v1 |
| https://arxiv.org/pdf/1909.07957v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-internal-learning-approach-to-video |
| Repo | |
| Framework | |
Visuomotor Understanding for Representation Learning of Driving Scenes
| Title | Visuomotor Understanding for Representation Learning of Driving Scenes |
| Authors | Seokju Lee, Junsik Kim, Tae-Hyun Oh, Yongseop Jeong, Donggeun Yoo, Stephen Lin, In So Kweon |
| Abstract | Dashboard cameras capture a tremendous amount of driving scene video each day. These videos are purposefully coupled with vehicle sensing data, such as from the speedometer and inertial sensors, providing an additional sensing modality for free. In this work, we leverage the large-scale unlabeled yet naturally paired data for visual representation learning in the driving scenario. A representation is learned in an end-to-end self-supervised framework for predicting dense optical flow from a single frame with paired sensing data. We postulate that success on this task requires the network to learn semantic and geometric knowledge in the ego-centric view. For example, forecasting a future view to be seen from a moving vehicle requires an understanding of scene depth, scale, and movement of objects. We demonstrate that our learned representation can benefit other tasks that require detailed scene understanding and outperforms competing unsupervised representations on semantic segmentation. |
| Tasks | Optical Flow Estimation, Representation Learning, Scene Understanding, Semantic Segmentation |
| Published | 2019-09-16 |
| URL | https://arxiv.org/abs/1909.06979v1 |
| https://arxiv.org/pdf/1909.06979v1.pdf | |
| PWC | https://paperswithcode.com/paper/visuomotor-understanding-for-representation |
| Repo | |
| Framework | |
Feature-Fused Context-Encoding Network for Neuroanatomy Segmentation
| Title | Feature-Fused Context-Encoding Network for Neuroanatomy Segmentation |
| Authors | Yuemeng Li, Hangfan Liu, Hongming Li, Yong Fan |
| Abstract | Automatic segmentation of fine-grained brain structures remains a challenging task. Current segmentation methods mainly utilize 2D and 3D deep neural networks. The 2D networks take image slices as input to produce coarse segmentation in less processing time, whereas the 3D networks take the whole image volumes to generated fine-detailed segmentation with more computational burden. In order to obtain accurate fine-grained segmentation efficiently, in this paper, we propose an end-to-end Feature-Fused Context-Encoding Network for brain structure segmentation from MR (magnetic resonance) images. Our model is implemented based on a 2D convolutional backbone, which integrates a 2D encoding module to acquire planar image features and a spatial encoding module to extract spatial context information. A global context encoding module is further introduced to capture global context semantics from the fused 2D encoding and spatial features. The proposed network aims to fully leverage the global anatomical prior knowledge learned from context semantics, which is represented by a structure-aware attention factor to recalibrate the outputs of the network. In this way, the network is guaranteed to be aware of the class-dependent feature maps to facilitate the segmentation. We evaluate our model on 2012 Brain Multi-Atlas Labelling Challenge dataset for 134 fine-grained structure segmentation. Besides, we validate our network on 27 coarse structure segmentation tasks. Experimental results have demonstrated that our model can achieve improved performance compared with the state-of-the-art approaches. |
| Tasks | |
| Published | 2019-05-07 |
| URL | https://arxiv.org/abs/1905.02686v1 |
| https://arxiv.org/pdf/1905.02686v1.pdf | |
| PWC | https://paperswithcode.com/paper/feature-fused-context-encoding-network-for |
| Repo | |
| Framework | |
Embedding Human Heuristics in Machine-Learning-Enabled Probe Microscopy
| Title | Embedding Human Heuristics in Machine-Learning-Enabled Probe Microscopy |
| Authors | O. Gordon, F. Junqueira, P. Moriarty |
| Abstract | Scanning probe microscopists generally do not rely on complete images to assess the quality of data acquired during a scan. Instead, assessments of the state of the tip apex, which not only determines the resolution in any scanning probe technique but can also generate a wide array of frustrating artefacts, are carried out in real time on the basis of a few lines of an image (and, typically, their associated line profiles.) The very small number of machine learning approaches to probe microscopy published to date, however, involve classifications based on full images. Given that data acquisition is the most time-consuming task during routine tip conditioning, automated methods are thus currently extremely slow in comparison to the tried-and-trusted strategies and heuristics used routinely by probe microscopists. Here, we explore various strategies by which different STM image classes (arising from changes in the tip state) can be correctly identified from partial scans. By employing a secondary temporal network and a rolling window of a small group of individual scanlines, we find that tip assessment is possible with a small fraction of a complete image. We achieve this with little-to-no performance penalty – or, indeed, markedly improved performance in some cases – and introduce a protocol to detect the state of the tip apex in real time. |
| Tasks | |
| Published | 2019-07-31 |
| URL | https://arxiv.org/abs/1907.13401v1 |
| https://arxiv.org/pdf/1907.13401v1.pdf | |
| PWC | https://paperswithcode.com/paper/embedding-human-heuristics-in-machine |
| Repo | |
| Framework | |
