January 29, 2020

3052 words 15 mins read

Paper Group ANR 641

Texture image analysis and texture classification methods - A review. Boundary-Preserved Deep Denoising of the Stochastic Resonance Enhanced Multiphoton Images. Naver Labs Europe’s Systems for the WMT19 Machine Translation Robustness Task. Making Sense of Vision and Touch: Learning Multimodal Representations for Contact-Rich Tasks. Composing Task-A …

Texture image analysis and texture classification methods - A review


Title	Texture image analysis and texture classification methods - A review
Authors	Laleh Armi, Shervan Fekri-Ershad
Abstract	Tactile texture refers to the tangible feel of a surface and visual texture refers to see the shape or contents of the image. In the image processing, the texture can be defined as a function of spatial variation of the brightness intensity of the pixels. Texture is the main term used to define objects or concepts of a given image. Texture analysis plays an important role in computer vision cases such as object recognition, surface defect detection, pattern recognition, medical image analysis, etc. Since now many approaches have been proposed to describe texture images accurately. Texture analysis methods usually are classified into four categories: statistical methods, structural, model-based and transform-based methods. This paper discusses the various methods used for texture or analysis in details. New researches shows the power of combinational methods for texture analysis, which can’t be in specific category. This paper provides a review on well known combinational methods in a specific section with details. This paper counts advantages and disadvantages of well-known texture image descriptors in the result part. Main focus in all of the survived methods is on discrimination performance, computational complexity and resistance to challenges such as noise, rotation, etc. A brief review is also made on the common classifiers used for texture image classification. Also, a survey on texture image benchmark datasets is included.
Tasks	Image Classification, Object Recognition, Texture Classification
Published	2019-04-13
URL	http://arxiv.org/abs/1904.06554v1
PDF	http://arxiv.org/pdf/1904.06554v1.pdf
PWC	https://paperswithcode.com/paper/texture-image-analysis-and-texture
Repo
Framework

Boundary-Preserved Deep Denoising of the Stochastic Resonance Enhanced Multiphoton Images


Title	Boundary-Preserved Deep Denoising of the Stochastic Resonance Enhanced Multiphoton Images
Authors	Sheng-Yong Niu, Lun-Zhang Guo, Yue Li, Tzung-Dau Wang, Yu Tsao, Tzu-Ming Liu
Abstract	As the rapid growth of high-speed and deep-tissue imaging in biomedical research, it is urgent to find a robust and effective denoising method to retain morphological features for further texture analysis and segmentation. Conventional denoising filters and models can easily suppress perturbative noises in high contrast images. However, for low photon budget multi-photon images, high detector gain will not only boost signals, but also bring huge background noises. In such stochastic resonance regime of imaging, sub-threshold signals may be detectable with the help of noises. Therefore, a denoising filter that can smartly remove noises without sacrificing the important cellular features such as cell boundaries is highly desired. In this paper, we propose a convolutional neural network based autoencoder method, Fully Convolutional Deep Denoising Autoencoder (DDAE), to improve the quality of Three-Photon Fluorescence (3PF) and Third Harmonic Generation (THG) microscopy images. The average of the acquired 200 images of a given location served as the low-noise answer for DDAE training. Compared with other widely used denoising methods, our DDAE model shows better signal-to-noise ratio (26.6 and 29.9 for 3PF and THG, respectively), structure similarity (0.86 and 0.87 for 3PF and THG, respectively), and preservation of nuclear or cellular boundaries.
Tasks	Denoising, Texture Classification
Published	2019-04-12
URL	http://arxiv.org/abs/1904.06329v2
PDF	http://arxiv.org/pdf/1904.06329v2.pdf
PWC	https://paperswithcode.com/paper/boundary-preserved-deep-denoising-of-the
Repo
Framework

Naver Labs Europe’s Systems for the WMT19 Machine Translation Robustness Task


Title	Naver Labs Europe’s Systems for the WMT19 Machine Translation Robustness Task
Authors	Alexandre Bérard, Ioan Calapodescu, Claude Roux
Abstract	This paper describes the systems that we submitted to the WMT19 Machine Translation robustness task. This task aims to improve MT’s robustness to noise found on social media, like informal language, spelling mistakes and other orthographic variations. The organizers provide parallel data extracted from a social media website in two language pairs: French-English and Japanese-English (in both translation directions). The goal is to obtain the best scores on unseen test sets from the same source, according to automatic metrics (BLEU) and human evaluation. We proposed one single and one ensemble system for each translation direction. Our ensemble models ranked first in all language pairs, according to BLEU evaluation. We discuss the pre-processing choices that we made, and present our solutions for robustness to noise and domain adaptation.
Tasks	Domain Adaptation, Machine Translation
Published	2019-07-15
URL	https://arxiv.org/abs/1907.06488v1
PDF	https://arxiv.org/pdf/1907.06488v1.pdf
PWC	https://paperswithcode.com/paper/naver-labs-europes-systems-for-the-wmt19
Repo
Framework

Making Sense of Vision and Touch: Learning Multimodal Representations for Contact-Rich Tasks


Title	Making Sense of Vision and Touch: Learning Multimodal Representations for Contact-Rich Tasks
Authors	Michelle A. Lee, Yuke Zhu, Peter Zachares, Matthew Tan, Krishnan Srinivasan, Silvio Savarese, Li Fei-Fei, Animesh Garg, Jeannette Bohg
Abstract	Contact-rich manipulation tasks in unstructured environments often require both haptic and visual feedback. It is non-trivial to manually design a robot controller that combines these modalities which have very different characteristics. While deep reinforcement learning has shown success in learning control policies for high-dimensional inputs, these algorithms are generally intractable to deploy on real robots due to sample complexity. In this work, we use self-supervision to learn a compact and multimodal representation of our sensory inputs, which can then be used to improve the sample efficiency of our policy learning. Evaluating our method on a peg insertion task, we show that it generalizes over varying geometries, configurations, and clearances, while being robust to external perturbations. We also systematically study different self-supervised learning objectives and representation learning architectures. Results are presented in simulation and on a physical robot.
Tasks	Representation Learning
Published	2019-07-28
URL	https://arxiv.org/abs/1907.13098v1
PDF	https://arxiv.org/pdf/1907.13098v1.pdf
PWC	https://paperswithcode.com/paper/making-sense-of-vision-and-touch-learning
Repo
Framework

Composing Task-Agnostic Policies with Deep Reinforcement Learning


Title	Composing Task-Agnostic Policies with Deep Reinforcement Learning
Authors	Ahmed H. Qureshi, Jacob J. Johnson, Yuzhe Qin, Taylor Henderson, Byron Boots, Michael C. Yip
Abstract	The composition of elementary behaviors to solve challenging transfer learning problems is one of the key elements in building intelligent machines. To date, there has been plenty of work on learning task-specific policies or skills but almost no focus on composing necessary, task-agnostic skills to find a solution to new problems. In this paper, we propose a novel deep reinforcement learning-based skill transfer and composition method that takes the agent’s primitive policies to solve unseen tasks. We evaluate our method in difficult cases where training policy through standard reinforcement learning (RL) or even hierarchical RL is either not feasible or exhibits high sample complexity. We show that our method not only transfers skills to new problem settings but also solves the challenging environments requiring both task planning and motion control with high data efficiency.
Tasks	Decision Making, Motion Planning, Transfer Learning
Published	2019-05-25
URL	https://arxiv.org/abs/1905.10681v2
PDF	https://arxiv.org/pdf/1905.10681v2.pdf
PWC	https://paperswithcode.com/paper/composing-ensembles-of-policies-with-deep
Repo
Framework

Quadratic Autoencoder (Q-AE) for Low-dose CT Denoising


Title	Quadratic Autoencoder (Q-AE) for Low-dose CT Denoising
Authors	Fenglei Fan, Hongming Shan, Mannudeep K. Kalra, Ramandeep Singh, Guhan Qian, Matthew Getzin, Yueyang Teng, Juergen Hahn, Ge Wang
Abstract	Inspired by complexity and diversity of biological neurons, our group proposed quadratic neurons by replacing the inner product in current artificial neurons with a quadratic operation on input data, thereby enhancing the capability of an individual neuron. Along this direction, we are motivated to evaluate the power of quadratic neurons in popular network architectures, simulating human-like learning in the form of quadratic-neuron-based deep learning. Our prior theoretical studies have shown important merits of quadratic neurons and networks in representation, efficiency, and interpretability. In this paper, we use quadratic neurons to construct an encoder-decoder structure, referred as the quadratic autoencoder, and apply it to low-dose CT denoising. The experimental results on the Mayo low-dose CT dataset demonstrate the utility of quadratic autoencoder in terms of image denoising and model efficiency. To our best knowledge, this is the first time that the deep learning approach is implemented with a new type of neurons and demonstrates a significant potential in the medical imaging field.
Tasks	Denoising, Image Denoising
Published	2019-01-17
URL	https://arxiv.org/abs/1901.05593v5
PDF	https://arxiv.org/pdf/1901.05593v5.pdf
PWC	https://paperswithcode.com/paper/quadratic-autoencoder-for-low-dose-ct
Repo
Framework

Stability Properties of Graph Neural Networks


Title	Stability Properties of Graph Neural Networks
Authors	Fernando Gama, Joan Bruna, Alejandro Ribeiro
Abstract	Graph neural networks (GNNs) have emerged as a powerful tool for nonlinear processing of graph signals, exhibiting success in traffic forecasting, recommender systems, power outage prediction, and motion planning, among others. GNNs consist of a cascade of layers, each of which applies a graph convolution, followed by a pointwise nonlinearity. In this work, we study the impact that changes in the underlying topology have on the output of the GNN. First, we show that GNNs are permutation equivariant, which implies that they effectively exploit internal symmetries of the underlying topology. Then, we prove that graph convolutions with integral Lipschitz filters, in combination with the frequency mixing effect of the corresponding nonlinearities, yields an architecture that is both stable to small changes in the underlying topology and discriminative of information located at high frequencies. These are two properties that cannot simultaneously hold when using only linear graph filters, which are either discriminative or stable, thus explaining the superior performance of GNNs.
Tasks	Motion Planning, Recommendation Systems
Published	2019-05-11
URL	https://arxiv.org/abs/1905.04497v2
PDF	https://arxiv.org/pdf/1905.04497v2.pdf
PWC	https://paperswithcode.com/paper/stability-properties-of-graph-neural-networks
Repo
Framework

Multi-band Weighted $l_p$ Norm Minimization for Image Denoising


Title	Multi-band Weighted $l_p$ Norm Minimization for Image Denoising
Authors	Yanchi Su, Zhanshan Li, Haihong Yu, Zeyu Wang
Abstract	Low rank matrix approximation (LRMA) has drawn increasing attention in recent years, due to its wide range of applications in computer vision and machine learning. However, LRMA, achieved by nuclear norm minimization (NNM), tends to over-shrink the rank components with the same threshold and ignore the differences between rank components. To address this problem, we propose a flexible and precise model named multi-band weighted $l_p$ norm minimization (MBWPNM). The proposed MBWPNM not only gives more accurate approximation with a Schatten $p$-norm, but also considers the prior knowledge where different rank components have different importance. We analyze the solution of MBWPNM and prove that MBWPNM is equivalent to a non-convex $l_p$ norm subproblems under certain weight condition, whose global optimum can be solved by a generalized soft-thresholding algorithm. We then adopt the MBWPNM algorithm to color and multispectral image denoising. Extensive experiments on additive white Gaussian noise removal and realistic noise removal demonstrate that the proposed MBWPNM achieves a better performance than several state-of-art algorithms.
Tasks	Denoising, Image Denoising
Published	2019-01-14
URL	https://arxiv.org/abs/1901.04206v4
PDF	https://arxiv.org/pdf/1901.04206v4.pdf
PWC	https://paperswithcode.com/paper/multi-band-weighted-l_p-norm-minimization-for
Repo
Framework

Zero-Shot Generation of Human-Object Interaction Videos


Title	Zero-Shot Generation of Human-Object Interaction Videos
Authors	Megha Nawhal, Mengyao Zhai, Andreas Lehrmann, Leonid Sigal
Abstract	Generation of videos of complex scenes is an important open problem in computer vision research. Human activity videos are a good example of such complex scenes. Human activities are typically formed as compositions of actions applied to objects – modeling interactions between people and the physical world are a core part of visual understanding. In this paper, we introduce the task of generating human-object interaction videos in a zero-shot compositional setting, i.e., generating videos for action-object compositions that are unseen during training, having seen the target action and target object independently. To generate human-object interaction videos, we propose a novel adversarial framework HOI-GAN which includes multiple discriminators focusing on different aspects of a video. To demonstrate the effectiveness of our proposed framework, we perform extensive quantitative and qualitative evaluation on two challenging datasets: EPIC-Kitchens and 20BN-Something-Something v2.
Tasks	Human-Object Interaction Detection
Published	2019-12-05
URL	https://arxiv.org/abs/1912.02401v2
PDF	https://arxiv.org/pdf/1912.02401v2.pdf
PWC	https://paperswithcode.com/paper/zero-shot-generation-of-human-object
Repo
Framework

Deep Multi-Sensor Lane Detection


Title	Deep Multi-Sensor Lane Detection
Authors	Min Bai, Gellert Mattyus, Namdar Homayounfar, Shenlong Wang, Shrinidhi Kowshika Lakshmikanth, Raquel Urtasun
Abstract	Reliable and accurate lane detection has been a long-standing problem in the field of autonomous driving. In recent years, many approaches have been developed that use images (or videos) as input and reason in image space. In this paper we argue that accurate image estimates do not translate to precise 3D lane boundaries, which are the input required by modern motion planning algorithms. To address this issue, we propose a novel deep neural network that takes advantage of both LiDAR and camera sensors and produces very accurate estimates directly in 3D space. We demonstrate the performance of our approach on both highways and in cities, and show very accurate estimates in complex scenarios such as heavy traffic (which produces occlusion), fork, merges and intersections.
Tasks	Autonomous Driving, Lane Detection, Motion Planning
Published	2019-05-04
URL	https://arxiv.org/abs/1905.01555v1
PDF	https://arxiv.org/pdf/1905.01555v1.pdf
PWC	https://paperswithcode.com/paper/deep-multi-sensor-lane-detection
Repo
Framework

BanditRank: Learning to Rank Using Contextual Bandits


Title	BanditRank: Learning to Rank Using Contextual Bandits
Authors	Phanideep Gampa, Sumio Fujita
Abstract	We propose an extensible deep learning method that uses reinforcement learning to train neural networks for offline ranking in information retrieval (IR). We call our method BanditRank as it treats ranking as a contextual bandit problem. In the domain of learning to rank for IR, current deep learning models are trained on objective functions different from the measures they are evaluated on. Since most evaluation measures are discrete quantities, they cannot be leveraged by directly using gradient descent algorithms without an approximation. BanditRank bridges this gap by directly optimizing a task-specific measure, such as mean average precision (MAP), using gradient descent. Specifically, a contextual bandit whose action is to rank input documents is trained using a policy gradient algorithm to directly maximize the reward. The reward can be a single measure, such as MAP, or a combination of several measures. The notion of ranking is also inherent in BanditRank, similar to the current \textit{listwise} approaches. To evaluate the effectiveness of BanditRank, we conducted a series of experiments on datasets related to three different tasks, i.e., web search, community, and factoid question answering. We found that it performs better than state-of-the-art methods when applied on the question answering datasets. On the web search dataset, we found that BanditRank performed better than four strong listwise baselines including LambdaMART, AdaRank, ListNet and Coordinate Ascent.
Tasks	Information Retrieval, Learning-To-Rank, Multi-Armed Bandits, Question Answering
Published	2019-10-23
URL	https://arxiv.org/abs/1910.10410v1
PDF	https://arxiv.org/pdf/1910.10410v1.pdf
PWC	https://paperswithcode.com/paper/banditrank-learning-to-rank-using-contextual
Repo
Framework

A Hybrid Algorithm for Metaheuristic Optimization


Title	A Hybrid Algorithm for Metaheuristic Optimization
Authors	Sujit Pramod Khanna, Alexander Ororbia II
Abstract	We propose a novel, flexible algorithm for combining together metaheuristicoptimizers for non-convex optimization problems. Our approach treatsthe constituent optimizers as a team of complex agents that communicateinformation amongst each other at various intervals during the simulationprocess. The information produced by each individual agent can be combinedin various ways via higher-level operators. In our experiments on keybenchmark functions, we investigate how the performance of our algorithmvaries with respect to several of its key modifiable properties. Finally,we apply our proposed algorithm to classification problems involving theoptimization of support-vector machine classifiers.
Tasks
Published	2019-05-26
URL	https://arxiv.org/abs/1906.02010v1
PDF	https://arxiv.org/pdf/1906.02010v1.pdf
PWC	https://paperswithcode.com/paper/190602010
Repo
Framework

Solution of Definite Integrals using Functional Link Artificial Neural Networks


Title	Solution of Definite Integrals using Functional Link Artificial Neural Networks
Authors	Satyasaran Changdar, Snehangshu Bhattacharjee
Abstract	This paper discusses a new method to solve definite integrals using artificial neural networks. The objective is to build a neural network that would be a novel alternative to pre-established numerical methods and with the help of a learning algorithm, be able to solve definite integrals, by minimising a well constructed error function. The proposed algorithm, with respect to existing numerical methods, is effective and precise and well-suited for purposes which require integration of higher order polynomials. The observations have been recorded and illustrated in tabular and graphical form.
Tasks
Published	2019-04-21
URL	http://arxiv.org/abs/1904.09656v1
PDF	http://arxiv.org/pdf/1904.09656v1.pdf
PWC	https://paperswithcode.com/paper/solution-of-definite-integrals-using
Repo
Framework

AttentionBoost: Learning What to Attend by Boosting Fully Convolutional Networks


Title	AttentionBoost: Learning What to Attend by Boosting Fully Convolutional Networks
Authors	Gozde Nur Gunesli, Cenk Sokmensuer, Cigdem Gunduz-Demir
Abstract	Dense prediction models are widely used for image segmentation. One important challenge is to sufficiently train these models to yield good generalizations for hard-to-learn pixels. A typical group of such hard-to-learn pixels are boundaries between instances. Many studies have proposed to give specific attention to learning the boundary pixels. They include designing multi-task networks with an additional task of boundary prediction and increasing the weights of boundary pixels’ predictions in the loss function. Such strategies require defining what to attend beforehand and incorporating this defined attention to the learning model. However, there may exist other groups of hard-to-learn pixels and manually defining and incorporating the appropriate attention for each group may not be feasible. In order to provide a more attainable and scalable solution, this paper proposes AttentionBoost, which is a new multi-attention learning model based on adaptive boosting. AttentionBoost designs a multi-stage network and introduces a new loss adjustment mechanism for a dense prediction model to adaptively learn what to attend at each stage directly on image data without necessitating any prior definition about what to attend. This mechanism modulates the attention of each stage to correct the mistakes of previous stages, by adjusting the loss weight of each pixel prediction separately with respect to how accurate the previous stages are on this pixel. This mechanism enables AttentionBoost to learn different attentions for different pixels at the same stage, according to difficulty of learning these pixels, as well as multiple attentions for the same pixel at different stages, according to confidence of these stages on their predictions for this pixel. Using gland segmentation as a showcase application, our experiments demonstrate that AttentionBoost improves the results of its counterparts.
Tasks	Semantic Segmentation
Published	2019-08-06
URL	https://arxiv.org/abs/1908.02095v1
PDF	https://arxiv.org/pdf/1908.02095v1.pdf
PWC	https://paperswithcode.com/paper/attentionboost-learning-what-to-attend-by
Repo
Framework

Integrating Association Rules with Decision Trees in Object-Relational Databases


Title	Integrating Association Rules with Decision Trees in Object-Relational Databases
Authors	Maruthi Rohit Ayyagari
Abstract	Research has provided evidence that associative classification produces more accurate results compared to other classification models. The Classification Based on Association (CBA) is one of the famous Associative Classification algorithms that generates accurate classifiers. However, current association classification algorithms reside external to databases, which reduces the flexibility of enterprise analytics systems. This paper implements the CBA in Oracle database using two variant models: hardcoding the CBA in Oracle Data Mining (ODM) package and Integrating Oracle Apriori model with the Oracle Decision tree model. We compared the proposed model performance with Naive Bayes, Support Vector Machine, Random Forests, and Decision Tree over 18 datasets from UCI. Results showed that our models outperformed the original CBA model with 1 percent and is competitive to chosen classification models over benchmark datasets.
Tasks
Published	2019-04-21
URL	http://arxiv.org/abs/1904.09654v1
PDF	http://arxiv.org/pdf/1904.09654v1.pdf
PWC	https://paperswithcode.com/paper/integrating-association-rules-with-decision
Repo
Framework