Paper Group ANR 1761
Layerwise Noise Maximisation to Train Low-Energy Deep Neural Networks. Shift Convolution Network for Stereo Matching. A multimodal movie review corpus for fine-grained opinion mining. Named Entity Recognition System for Sindhi Language. Deep Network Approximation Characterized by Number of Neurons. A Robust Regression Approach for Robot Model Learn …
Layerwise Noise Maximisation to Train Low-Energy Deep Neural Networks
| Title | Layerwise Noise Maximisation to Train Low-Energy Deep Neural Networks |
| Authors | Sébastien Henwood, François Leduc-Primeau, Yvon Savaria |
| Abstract | Deep neural networks (DNNs) depend on the storage of a large number of parameters, which consumes an important portion of the energy used during inference. This paper considers the case where the energy usage of memory elements can be reduced at the cost of reduced reliability. A training algorithm is proposed to optimize the reliability of the storage separately for each layer of the network, while incurring a negligible complexity overhead compared to a conventional stochastic gradient descent training. For an exponential energy-reliability model, the proposed training approach can decrease the memory energy consumption of a DNN with binary parameters by 3.3$\times$ at isoaccuracy, compared to a reliable implementation. |
| Tasks | |
| Published | 2019-12-23 |
| URL | https://arxiv.org/abs/1912.10764v1 |
| https://arxiv.org/pdf/1912.10764v1.pdf | |
| PWC | https://paperswithcode.com/paper/layerwise-noise-maximisation-to-train-low |
| Repo | |
| Framework | |
Shift Convolution Network for Stereo Matching
| Title | Shift Convolution Network for Stereo Matching |
| Authors | Jian Xie |
| Abstract | In this paper, we present Shift Convolution Network (ShiftConvNet) to provide matching capability between two feature maps for stereo estimation. The proposed method can speedily produce a highly accurate disparity map from stereo images. A module called shift convolution layer is proposed to replace the traditional correlation layer to perform patch comparisons between two feature maps. By using a novel architecture of convolutional network to learn the matching process, ShiftConvNet can produce better results than DispNet-C[1], also running faster with 5 fps. Moreover, with a proposed auto shift convolution refine part, further improvement is obtained. The proposed approach was evaluated on FlyingThings 3D. It achieves state-of-the-art results on the benchmark dataset. Codes will be made available at github. |
| Tasks | Stereo Matching |
| Published | 2019-11-20 |
| URL | https://arxiv.org/abs/1911.08896v1 |
| https://arxiv.org/pdf/1911.08896v1.pdf | |
| PWC | https://paperswithcode.com/paper/shift-convolution-network-for-stereo-matching |
| Repo | |
| Framework | |
A multimodal movie review corpus for fine-grained opinion mining
| Title | A multimodal movie review corpus for fine-grained opinion mining |
| Authors | Alexandre Garcia, Slim Essid, Florence d’Alché-Buc, Chloé Clavel |
| Abstract | In this paper, we introduce a set of opinion annotations for the POM movie review dataset, composed of 1000 videos. The annotation campaign is motivated by the development of a hierarchical opinion prediction framework allowing one to predict the different components of the opinions (e.g. polarity and aspect) and to identify the corresponding textual spans. The resulting annotations have been gathered at two granularity levels: a coarse one (opinionated span) and a finer one (span of opinion components). We introduce specific categories in order to make the annotation of opinions easier for movie reviews. For example, some categories allow the discovery of user recommendation and preference in movie reviews. We provide a quantitative analysis of the annotations and report the inter-annotator agreement under the different levels of granularity. We provide thus the first set of ground-truth annotations which can be used for the task of fine-grained multimodal opinion prediction. We provide an analysis of the data gathered through an inter-annotator study and show that a linear structured predictor learns meaningful features even for the prediction of scarce labels. Both the annotations and the baseline system will be made publicly available. |
| Tasks | Opinion Mining |
| Published | 2019-02-26 |
| URL | http://arxiv.org/abs/1902.10102v1 |
| http://arxiv.org/pdf/1902.10102v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-multimodal-movie-review-corpus-for-fine |
| Repo | |
| Framework | |
Named Entity Recognition System for Sindhi Language
| Title | Named Entity Recognition System for Sindhi Language |
| Authors | Awais Khan Jumani, Mashooque Ahmed Memon, Fida Hussain Khoso, Anwar Ali Sanjrani, Safeeullah Soomro |
| Abstract | Named Entity Recognition (NER) System aims to extract the existing information into the following categories such as: Persons Name, Organization, Location, Date and Time, Term, Designation and Short forms. Now, it is considered to be important aspect for many natural languages processing (NLP) tasks such as: information retrieval system, machine translation system, information extraction system and question answering. Even at a surface level, the understanding of the named entities involved in a document gives richer analytical framework and cross referencing. It has been used for different Arabic Script-Based languages like, Arabic, Persian and Urdu but, Sindhi could not come into being yet. This paper explains the problem of NER in the framework of Sindhi Language and provides relevant solution. The system is developed to tag ten different Named Entities. We have used Ruled based approach for NER system of Sindhi Language. For the training and testing, 936 words were used and calculated performance accuracy of 98.71%. |
| Tasks | Information Retrieval, Machine Translation, Named Entity Recognition, Question Answering |
| Published | 2019-09-28 |
| URL | https://arxiv.org/abs/1910.03475v1 |
| https://arxiv.org/pdf/1910.03475v1.pdf | |
| PWC | https://paperswithcode.com/paper/named-entity-recognition-system-for-sindhi |
| Repo | |
| Framework | |
Deep Network Approximation Characterized by Number of Neurons
| Title | Deep Network Approximation Characterized by Number of Neurons |
| Authors | Zuowei Shen, Haizhao Yang, Shijun Zhang |
| Abstract | This paper quantitatively characterizes the approximation power of deep feed-forward neural networks (FNNs) in terms of the number of neurons, i.e., the product of the network width and depth. It is shown by construction that ReLU FNNs with width $\mywidth$ and depth $9L+12$ can approximate an arbitrary H"older continuous function of order $\alpha$ with a Lipschitz constant $\nu$ on $[0,1]^d$ with a tight approximation rate $5(8\sqrt{d})^\alpha\nu N^{-2\alpha/d}L^{-2\alpha/d}$ for any given $N,L\in \N^+$. The constructive approximation is a corollary of a more general result for an arbitrary continuous function $f$ in terms of its modulus of continuity $\omega_f(\cdot)$. In particular, the approximation rate of ReLU FNNs with width $\mywidth$ and depth $9L+12$ for a general continuous function $f$ is $5\omega_f(8\sqrt{d} N^{-2/d}L^{-2/d})$. We also extend our analysis to the case when the domain of $f$ is irregular or localized in an $\epsilon$-neighborhood of a $d_{\mathcal{M}}$-dimensional smooth manifold $\mathcal{M}\subseteq [0,1]^d$ with $d_{\mathcal{M}}\ll d$. Especially, in the case of an essentially low-dimensional domain, we show an approximation rate $3\omega_f\big(\tfrac{4\epsilon}{1-\delta}\sqrt{\tfrac{d}{d_\delta}}\big)+5\omega_f\big(\tfrac{16d}{(1-\delta)\sqrt{d_\delta}}N^{-2/d_\delta}L^{-2/d_\delta }\big)$ for ReLU FNNs to approximate $f$ in the $\epsilon$-neighborhood, where $d_\delta=\OO\big(d_{\mathcal{M}}\tfrac{\ln (d/\delta)}{\delta^2}\big)$ for any given $\delta\in(0,1)$. Our analysis provides a general guide for selecting the width and the depth of ReLU FNNs to approximate continuous functions especially in parallel computing. |
| Tasks | |
| Published | 2019-06-13 |
| URL | https://arxiv.org/abs/1906.05497v1 |
| https://arxiv.org/pdf/1906.05497v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-network-approximation-characterized-by |
| Repo | |
| Framework | |
A Robust Regression Approach for Robot Model Learning
| Title | A Robust Regression Approach for Robot Model Learning |
| Authors | Francesco Cursi, Guang-Zhong Yang |
| Abstract | Machine learning and data analysis have been used in many robotics fields, especially for modelling. Data are usually the result of sensor measurements and, as such, they might be subjected to noise and outliers. The presence of outliers has a huge impact on modelling the acquired data, resulting in inappropriate models. In this work a novel approach for outlier detection and rejection for input/output mapping in regression problems is presented. The robustness of the method is shown both through simulated data for linear and nonlinear regression, and real sensory data. Despite being validated by using artificial neural networks, the method can be generalized to any other regression method |
| Tasks | Outlier Detection |
| Published | 2019-08-23 |
| URL | https://arxiv.org/abs/1908.08855v1 |
| https://arxiv.org/pdf/1908.08855v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-robust-regression-approach-for-robot-model |
| Repo | |
| Framework | |
On the Information Leakage in Private Information Retrieval Systems
| Title | On the Information Leakage in Private Information Retrieval Systems |
| Authors | Tao Guo, Ruida Zhou, Chao Tian |
| Abstract | We consider information leakage to the user in private information retrieval (PIR) systems. Information leakage can be measured in terms of individual message leakage or total leakage. Individual message leakage, or simply individual leakage, is defined as the amount of information that the user can obtain on any individual message that is not being requested, and the total leakage is defined as the amount of information that the user can obtain about all the other messages except the one being requested. In this work, we characterize the tradeoff between the minimum download cost and the individual leakage, and that for the total leakage, respectively. New codes are proposed to achieve these optimal tradeoffs, which are also shown to be optimal in terms of the message size. We further characterize the optimal tradeoff between the minimum amount of common randomness and the total leakage. Moreover, we show that under individual leakage, common randomness is in fact unnecessary when there are more than two messages. |
| Tasks | Information Retrieval |
| Published | 2019-09-25 |
| URL | https://arxiv.org/abs/1909.11605v2 |
| https://arxiv.org/pdf/1909.11605v2.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-information-leakage-in-private |
| Repo | |
| Framework | |
Random Walks on Hypergraphs with Edge-Dependent Vertex Weights
| Title | Random Walks on Hypergraphs with Edge-Dependent Vertex Weights |
| Authors | Uthsav Chitra, Benjamin J Raphael |
| Abstract | Hypergraphs are used in machine learning to model higher-order relationships in data. While spectral methods for graphs are well-established, spectral theory for hypergraphs remains an active area of research. In this paper, we use random walks to develop a spectral theory for hypergraphs with edge-dependent vertex weights: hypergraphs where every vertex $v$ has a weight $\gamma_e(v)$ for each incident hyperedge $e$ that describes the contribution of $v$ to the hyperedge $e$. We derive a random walk-based hypergraph Laplacian, and bound the mixing time of random walks on such hypergraphs. Moreover, we give conditions under which random walks on such hypergraphs are equivalent to random walks on graphs. As a corollary, we show that current machine learning methods that rely on Laplacians derived from random walks on hypergraphs with edge-independent vertex weights do not utilize higher-order relationships in the data. Finally, we demonstrate the advantages of hypergraphs with edge-dependent vertex weights on ranking applications using real-world datasets. |
| Tasks | |
| Published | 2019-05-20 |
| URL | https://arxiv.org/abs/1905.08287v1 |
| https://arxiv.org/pdf/1905.08287v1.pdf | |
| PWC | https://paperswithcode.com/paper/random-walks-on-hypergraphs-with-edge |
| Repo | |
| Framework | |
Incremental Answer Set Programming with Overgrounding
| Title | Incremental Answer Set Programming with Overgrounding |
| Authors | Francesco Calimeri, Giovambattista Ianni, Francesco Pacenza, Simona Perri, Jessica Zangari |
| Abstract | Repeated executions of reasoning tasks for varying inputs are necessary in many applicative settings, such as stream reasoning. In this context, we propose an incremental grounding approach for the answer set semantics. We focus on the possibility of generating incrementally larger ground logic programs equivalent to a given non-ground one; so called overgrounded programs can be reused in combination with deliberately many different sets of inputs. Updating overgrounded programs requires a small effort, thus making the instantiation of logic programs considerably faster when grounding is repeated on a series of inputs similar to each other. Notably, the proposed approach works “under the hood”, relieving designers of logic programs from controlling technical aspects of grounding engines and answer set systems. In this work we present the theoretical basis of the proposed incremental grounding technique, we illustrate the consequent repeated evaluation strategy and report about our experiments. This paper is under consideration in Theory and Practice of Logic Programming (TPLP). |
| Tasks | |
| Published | 2019-07-22 |
| URL | https://arxiv.org/abs/1907.09212v1 |
| https://arxiv.org/pdf/1907.09212v1.pdf | |
| PWC | https://paperswithcode.com/paper/incremental-answer-set-programming-with |
| Repo | |
| Framework | |
Sign-OPT: A Query-Efficient Hard-label Adversarial Attack
| Title | Sign-OPT: A Query-Efficient Hard-label Adversarial Attack |
| Authors | Minhao Cheng, Simranjit Singh, Patrick Chen, Pin-Yu Chen, Sijia Liu, Cho-Jui Hsieh |
| Abstract | We study the most practical problem setup for evaluating adversarial robustness of a machine learning system with limited access: the hard-label black-box attack setting for generating adversarial examples, where limited model queries are allowed and only the decision is provided to a queried data input. Several algorithms have been proposed for this problem but they typically require huge amount (>20,000) of queries for attacking one example. Among them, one of the state-of-the-art approaches (Cheng et al., 2019) showed that hard-label attack can be modeled as an optimization problem where the objective function can be evaluated by binary search with additional model queries, thereby a zeroth order optimization algorithm can be applied. In this paper, we adopt the same optimization formulation but propose to directly estimate the sign of gradient at any direction instead of the gradient itself, which enjoys the benefit of single query. Using this single query oracle for retrieving sign of directional derivative, we develop a novel query-efficient Sign-OPT approach for hard-label black-box attack. We provide a convergence analysis of the new algorithm and conduct experiments on several models on MNIST, CIFAR-10 and ImageNet. We find that Sign-OPT attack consistently requires 5X to 10X fewer queries when compared to the current state-of-the-art approaches, and usually converges to an adversarial example with smaller perturbation. |
| Tasks | Adversarial Attack |
| Published | 2019-09-24 |
| URL | https://arxiv.org/abs/1909.10773v3 |
| https://arxiv.org/pdf/1909.10773v3.pdf | |
| PWC | https://paperswithcode.com/paper/sign-opt-a-query-efficient-hard-label |
| Repo | |
| Framework | |
Camera Pose Correction in SLAM Based on Bias Values of Map Points
| Title | Camera Pose Correction in SLAM Based on Bias Values of Map Points |
| Authors | Zhaobing Kang, Wei Zou, Zheng Zhu |
| Abstract | Accurate camera pose estimation result is essential for visual SLAM (VSLAM). This paper presents a novel pose correction method to improve the accuracy of the VSLAM system. Firstly, the relationship between the camera pose estimation error and bias values of map points is derived based on the optimized function in VSLAM. Secondly, the bias value of the map point is calculated by a statistical method. Finally, the camera pose estimation error is compensated according to the first derived relationship. After the pose correction, procedures of the original system, such as the bundle adjustment (BA) optimization, can be executed as before. Compared with existing methods, our algorithm is compact and effective and can be easily generalized to different VSLAM systems. Additionally, the robustness to system noise of our method is better than feature selection methods, due to all original system information is preserved in our algorithm while only a subset is employed in the latter. Experimental results on benchmark datasets show that our approach leads to considerable improvements over state-of-the-art algorithms for absolute pose estimation. |
| Tasks | Feature Selection, Pose Estimation |
| Published | 2019-08-24 |
| URL | https://arxiv.org/abs/1908.09072v1 |
| https://arxiv.org/pdf/1908.09072v1.pdf | |
| PWC | https://paperswithcode.com/paper/camera-pose-correction-in-slam-based-on-bias |
| Repo | |
| Framework | |
Low-Resource Corpus Filtering using Multilingual Sentence Embeddings
| Title | Low-Resource Corpus Filtering using Multilingual Sentence Embeddings |
| Authors | Vishrav Chaudhary, Yuqing Tang, Francisco Guzmán, Holger Schwenk, Philipp Koehn |
| Abstract | In this paper, we describe our submission to the WMT19 low-resource parallel corpus filtering shared task. Our main approach is based on the LASER toolkit (Language-Agnostic SEntence Representations), which uses an encoder-decoder architecture trained on a parallel corpus to obtain multilingual sentence representations. We then use the representations directly to score and filter the noisy parallel sentences without additionally training a scoring function. We contrast our approach to other promising methods and show that LASER yields strong results. Finally, we produce an ensemble of different scoring methods and obtain additional gains. Our submission achieved the best overall performance for both the Nepali-English and Sinhala-English 1M tasks by a margin of 1.3 and 1.4 BLEU respectively, as compared to the second best systems. Moreover, our experiments show that this technique is promising for low and even no-resource scenarios. |
| Tasks | Sentence Embeddings |
| Published | 2019-06-20 |
| URL | https://arxiv.org/abs/1906.08885v1 |
| https://arxiv.org/pdf/1906.08885v1.pdf | |
| PWC | https://paperswithcode.com/paper/low-resource-corpus-filtering-using |
| Repo | |
| Framework | |
Gated Embeddings in End-to-End Speech Recognition for Conversational-Context Fusion
| Title | Gated Embeddings in End-to-End Speech Recognition for Conversational-Context Fusion |
| Authors | Suyoun Kim, Siddharth Dalmia, Florian Metze |
| Abstract | We present a novel conversational-context aware end-to-end speech recognizer based on a gated neural network that incorporates conversational-context/word/speech embeddings. Unlike conventional speech recognition models, our model learns longer conversational-context information that spans across sentences and is consequently better at recognizing long conversations. Specifically, we propose to use the text-based external word and/or sentence embeddings (i.e., fastText, BERT) within an end-to-end framework, yielding a significant improvement in word error rate with better conversational-context representation. We evaluated the models on the Switchboard conversational speech corpus and show that our model outperforms standard end-to-end speech recognition models. |
| Tasks | End-To-End Speech Recognition, Sentence Embeddings, Speech Recognition |
| Published | 2019-06-27 |
| URL | https://arxiv.org/abs/1906.11604v1 |
| https://arxiv.org/pdf/1906.11604v1.pdf | |
| PWC | https://paperswithcode.com/paper/gated-embeddings-in-end-to-end-speech |
| Repo | |
| Framework | |
A Dynamical Systems Perspective on Nesterov Acceleration
| Title | A Dynamical Systems Perspective on Nesterov Acceleration |
| Authors | Michael Muehlebach, Michael I. Jordan |
| Abstract | We present a dynamical system framework for understanding Nesterov’s accelerated gradient method. In contrast to earlier work, our derivation does not rely on a vanishing step size argument. We show that Nesterov acceleration arises from discretizing an ordinary differential equation with a semi-implicit Euler integration scheme. We analyze both the underlying differential equation as well as the discretization to obtain insights into the phenomenon of acceleration. The analysis suggests that a curvature-dependent damping term lies at the heart of the phenomenon. We further establish connections between the discretized and the continuous-time dynamics. |
| Tasks | |
| Published | 2019-05-17 |
| URL | https://arxiv.org/abs/1905.07436v1 |
| https://arxiv.org/pdf/1905.07436v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-dynamical-systems-perspective-on-nesterov |
| Repo | |
| Framework | |
Adversarial Objects Against LiDAR-Based Autonomous Driving Systems
| Title | Adversarial Objects Against LiDAR-Based Autonomous Driving Systems |
| Authors | Yulong Cao, Chaowei Xiao, Dawei Yang, Jing Fang, Ruigang Yang, Mingyan Liu, Bo Li |
| Abstract | Deep neural networks (DNNs) are found to be vulnerable against adversarial examples, which are carefully crafted inputs with a small magnitude of perturbation aiming to induce arbitrarily incorrect predictions. Recent studies show that adversarial examples can pose a threat to real-world security-critical applications: a “physical adversarial Stop Sign” can be synthesized such that the autonomous driving cars will misrecognize it as others (e.g., a speed limit sign). However, these image-space adversarial examples cannot easily alter 3D scans of widely equipped LiDAR or radar on autonomous vehicles. In this paper, we reveal the potential vulnerabilities of LiDAR-based autonomous driving detection systems, by proposing an optimization based approach LiDAR-Adv to generate adversarial objects that can evade the LiDAR-based detection system under various conditions. We first show the vulnerabilities using a blackbox evolution-based algorithm, and then explore how much a strong adversary can do, using our gradient-based approach LiDAR-Adv. We test the generated adversarial objects on the Baidu Apollo autonomous driving platform and show that such physical systems are indeed vulnerable to the proposed attacks. We also 3D-print our adversarial objects and perform physical experiments to illustrate that such vulnerability exists in the real world. Please find more visualizations and results on the anonymous website: https://sites.google.com/view/lidar-adv. |
| Tasks | Autonomous Driving, Autonomous Vehicles |
| Published | 2019-07-11 |
| URL | https://arxiv.org/abs/1907.05418v1 |
| https://arxiv.org/pdf/1907.05418v1.pdf | |
| PWC | https://paperswithcode.com/paper/adversarial-objects-against-lidar-based |
| Repo | |
| Framework | |
