October 20, 2019

3117 words 15 mins read

Paper Group AWR 197

Learning Attraction Field Representation for Robust Line Segment Detection. Malaria Detection Using Image Processing and Machine Learning. Deeply learning molecular structure-property relationships using attention- and gate-augmented graph convolutional network. DeepDTA: Deep Drug-Target Binding Affinity Prediction. High-dimension Tensor Completion …

Learning Attraction Field Representation for Robust Line Segment Detection


Title	Learning Attraction Field Representation for Robust Line Segment Detection
Authors	Nan Xue, Song Bai, Fudong Wang, Gui-Song Xia, Tianfu Wu, Liangpei Zhang
Abstract	This paper presents a region-partition based attraction field dual representation for line segment maps, and thus poses the problem of line segment detection (LSD) as the region coloring problem. The latter is then addressed by learning deep convolutional neural networks (ConvNets) for accuracy, robustness and efficiency. For a 2D line segment map, our dual representation consists of three components: (i) A region-partition map in which every pixel is assigned to one and only one line segment; (ii) An attraction field map in which every pixel in a partition region is encoded by its 2D projection vector w.r.t. the associated line segment; and (iii) A squeeze module which squashes the attraction field to a line segment map that almost perfectly recovers the input one. By leveraging the duality, we learn ConvNets to compute the attraction field maps for raw in-put images, followed by the squeeze module for LSD, in an end-to-end manner. Our method rigorously addresses several challenges in LSD such as local ambiguity and class imbalance. Our method also harnesses the best practices developed in ConvNets based semantic segmentation methods such as the encoder-decoder architecture and the a-trous convolution. In experiments, our method is tested on the WireFrame dataset and the YorkUrban dataset with state-of-the-art performance obtained. Especially, we advance the performance by 4.5 percents on the WireFrame dataset. Our method is also fast with 6.6~10.4 FPS, outperforming most of existing line segment detectors.
Tasks	Line Segment Detection, Semantic Segmentation
Published	2018-12-05
URL	http://arxiv.org/abs/1812.02122v2
PDF	http://arxiv.org/pdf/1812.02122v2.pdf
PWC	https://paperswithcode.com/paper/learning-attraction-field-representation-for
Repo	https://github.com/cherubicXN/afm_cvpr2019
Framework	pytorch

Malaria Detection Using Image Processing and Machine Learning


Title	Malaria Detection Using Image Processing and Machine Learning
Authors	Suman Kunwar
Abstract	Malaria is mosquito-borne blood disease caused by parasites of the genus Plasmodium. Conventional diagnostic tool for malaria is the examination of stained blood cell of patient in microscope. The blood to be tested is placed in a slide and is observed under a microscope to count the number of infected RBC. An expert technician is involved in the examination of the slide with intense visual and mental concentration. This is tiresome and time consuming process. In this paper, we construct a new mage processing system for detection and quantification of plasmodium parasites in blood smear slide, later we develop Machine Learning algorithm to learn, detect and determine the types of infected cells according to its features.
Tasks
Published	2018-01-28
URL	http://arxiv.org/abs/1801.10031v2
PDF	http://arxiv.org/pdf/1801.10031v2.pdf
PWC	https://paperswithcode.com/paper/malaria-detection-using-image-processing-and
Repo	https://github.com/sumn2u/react-typescript-pdf-reader
Framework	none

Deeply learning molecular structure-property relationships using attention- and gate-augmented graph convolutional network


Title	Deeply learning molecular structure-property relationships using attention- and gate-augmented graph convolutional network
Authors	Seongok Ryu, Jaechang Lim, Seung Hwan Hong, Woo Youn Kim
Abstract	Molecular structure-property relationships are key to molecular engineering for materials and drug discovery. The rise of deep learning offers a new viable solution to elucidate the structure-property relationships directly from chemical data. Here we show that the performance of graph convolutional networks (GCNs) for the prediction of molecular properties can be improved by incorporating attention and gate mechanisms. The attention mechanism enables a GCN to identify atoms in different environments. The gated skip-connection further improves the GCN by updating feature maps at an appropriate rate. We demonstrate that the resulting attention- and gate-augmented GCN could extract better structural features related to a target molecular property such as solubility, polarity, synthetic accessibility and photovoltaic efficiency compared to the vanilla GCN. More interestingly, it identified two distinct parts of molecules as essential structural features for high photovoltaic efficiency, and each of them coincided with the areas of donor and acceptor orbitals for charge-transfer excitations, respectively. As a result, the new model could accurately predict molecular properties and place molecules with similar properties close to each other in a well-trained latent space, which is critical for successful molecular engineering.
Tasks	Drug Discovery
Published	2018-05-28
URL	http://arxiv.org/abs/1805.10988v3
PDF	http://arxiv.org/pdf/1805.10988v3.pdf
PWC	https://paperswithcode.com/paper/deeply-learning-molecular-structure-property
Repo	https://github.com/qyuan7/molecular_gcn
Framework	pytorch

DeepDTA: Deep Drug-Target Binding Affinity Prediction


Title	DeepDTA: Deep Drug-Target Binding Affinity Prediction
Authors	Hakime Öztürk, Elif Ozkirimli, Arzucan Özgür
Abstract	The identification of novel drug-target (DT) interactions is a substantial part of the drug discovery process. Most of the computational methods that have been proposed to predict DT interactions have focused on binary classification, where the goal is to determine whether a DT pair interacts or not. However, protein-ligand interactions assume a continuum of binding strength values, also called binding affinity and predicting this value still remains a challenge. The increase in the affinity data available in DT knowledge-bases allows the use of advanced learning techniques such as deep learning architectures in the prediction of binding affinities. In this study, we propose a deep-learning based model that uses only sequence information of both targets and drugs to predict DT interaction binding affinities. The few studies that focus on DT binding affinity prediction use either 3D structures of protein-ligand complexes or 2D features of compounds. One novel approach used in this work is the modeling of protein sequences and compound 1D representations with convolutional neural networks (CNNs). The results show that the proposed deep learning based model that uses the 1D representations of targets and drugs is an effective approach for drug target binding affinity prediction. The model in which high-level representations of a drug and a target are constructed via CNNs achieved the best Concordance Index (CI) performance in one of our larger benchmark data sets, outperforming the KronRLS algorithm and SimBoost, a state-of-the-art method for DT binding affinity prediction.
Tasks	Drug Discovery
Published	2018-01-30
URL	http://arxiv.org/abs/1801.10193v2
PDF	http://arxiv.org/pdf/1801.10193v2.pdf
PWC	https://paperswithcode.com/paper/deepdta-deep-drug-target-binding-affinity
Repo	https://github.com/Yindong-Zhang/GraphConvolutionDrugTargetInteration
Framework	tf

High-dimension Tensor Completion via Gradient-based Optimization Under Tensor-train Format


Title	High-dimension Tensor Completion via Gradient-based Optimization Under Tensor-train Format
Authors	Longhao Yuan, Qibin Zhao, Lihua Gui, Jianting Cao
Abstract	Tensor train (TT) decomposition has drawn people’s attention due to its powerful representation ability and performance stability in high-order tensors. In this paper, we propose a novel approach to recover the missing entries of incomplete data represented by higher-order tensors. We attempt to find the low-rank TT decomposition of the incomplete data which captures the latent features of the whole data and then reconstruct the missing entries. By applying gradient descent algorithms, tensor completion problem is efficiently solved by optimization models. We propose two TT-based algorithms: Tensor Train Weighted Optimization (TT-WOPT) and Tensor Train Stochastic Gradient Descent (TT-SGD) to optimize TT decomposition factors. In addition, a method named Visual Data Tensorization (VDT) is proposed to transform visual data into higher-order tensors, resulting in the performance improvement of our algorithms. The experiments in synthetic data and visual data show high efficiency and performance of our algorithms compared to the state-of-the-art completion algorithms, especially in high-order, high missing rate, and large-scale tensor completion situations.
Tasks
Published	2018-04-05
URL	http://arxiv.org/abs/1804.01983v3
PDF	http://arxiv.org/pdf/1804.01983v3.pdf
PWC	https://paperswithcode.com/paper/high-dimension-tensor-completion-via-gradient
Repo	https://github.com/yuanlonghao/T3C_tensor_completion
Framework	none

Tensor Ring Decomposition with Rank Minimization on Latent Space: An Efficient Approach for Tensor Completion


Title	Tensor Ring Decomposition with Rank Minimization on Latent Space: An Efficient Approach for Tensor Completion
Authors	Longhao Yuan, Chao Li, Danilo Mandic, Jianting Cao, Qibin Zhao
Abstract	In tensor completion tasks, the traditional low-rank tensor decomposition models suffer from the laborious model selection problem due to their high model sensitivity. In particular, for tensor ring (TR) decomposition, the number of model possibilities grows exponentially with the tensor order, which makes it rather challenging to find the optimal TR decomposition. In this paper, by exploiting the low-rank structure of the TR latent space, we propose a novel tensor completion method which is robust to model selection. In contrast to imposing the low-rank constraint on the data space, we introduce nuclear norm regularization on the latent TR factors, resulting in the optimization step using singular value decomposition (SVD) being performed at a much smaller scale. By leveraging the alternating direction method of multipliers (ADMM) scheme, the latent TR factors with optimal rank and the recovered tensor can be obtained simultaneously. Our proposed algorithm is shown to effectively alleviate the burden of TR-rank selection, thereby greatly reducing the computational cost. The extensive experimental results on both synthetic and real-world data demonstrate the superior performance and efficiency of the proposed approach against the state-of-the-art algorithms.
Tasks	Model Selection
Published	2018-09-07
URL	http://arxiv.org/abs/1809.02288v2
PDF	http://arxiv.org/pdf/1809.02288v2.pdf
PWC	https://paperswithcode.com/paper/tensor-ring-decomposition-with-rank
Repo	https://github.com/zhaoxile/reproducible-tensor-completion-state-of-the-art
Framework	none

Representation Flow for Action Recognition


Title	Representation Flow for Action Recognition
Authors	AJ Piergiovanni, Michael S. Ryoo
Abstract	In this paper, we propose a convolutional layer inspired by optical flow algorithms to learn motion representations. Our representation flow layer is a fully-differentiable layer designed to capture the `flow' of any representation channel within a convolutional neural network for action recognition. Its parameters for iterative flow optimization are learned in an end-to-end fashion together with the other CNN model parameters, maximizing the action recognition performance. Furthermore, we newly introduce the concept of learning` flow of flow’ representations by stacking multiple representation flow layers. We conducted extensive experimental evaluations, confirming its advantages over previous recognition models using traditional optical flows in both computational speed and performance. Code/models available here: https://piergiaj.github.io/rep-flow-site/
Tasks	Action Classification, Action Recognition In Videos, Activity Recognition, Activity Recognition In Videos, Optical Flow Estimation, Temporal Action Localization, Video Classification, Video Understanding
Published	2018-10-02
URL	https://arxiv.org/abs/1810.01455v3
PDF	https://arxiv.org/pdf/1810.01455v3.pdf
PWC	https://paperswithcode.com/paper/representation-flow-for-action-recognition
Repo	https://github.com/piergiaj/representation-flow-cvpr19
Framework	pytorch

Hybrid Binary Networks: Optimizing for Accuracy, Efficiency and Memory


Title	Hybrid Binary Networks: Optimizing for Accuracy, Efficiency and Memory
Authors	Ameya Prabhu, Vishal Batchu, Rohit Gajawada, Sri Aurobindo Munagala, Anoop Namboodiri
Abstract	Binarization is an extreme network compression approach that provides large computational speedups along with energy and memory savings, albeit at significant accuracy costs. We investigate the question of where to binarize inputs at layer-level granularity and show that selectively binarizing the inputs to specific layers in the network could lead to significant improvements in accuracy while preserving most of the advantages of binarization. We analyze the binarization tradeoff using a metric that jointly models the input binarization-error and computational cost and introduce an efficient algorithm to select layers whose inputs are to be binarized. Practical guidelines based on insights obtained from applying the algorithm to a variety of models are discussed. Experiments on Imagenet dataset using AlexNet and ResNet-18 models show 3-4% improvements in accuracy over fully binarized networks with minimal impact on compression and computational speed. The improvements are even more substantial on sketch datasets like TU-Berlin, where we match state-of-the-art accuracy as well, getting over 8% increase in accuracies. We further show that our approach can be applied in tandem with other forms of compression that deal with individual layers or overall model compression (e.g., SqueezeNets). Unlike previous quantization approaches, we are able to binarize the weights in the last layers of a network, which often have a large number of parameters, resulting in significant improvement in accuracy over fully binarized models.
Tasks	Model Compression, Quantization
Published	2018-04-11
URL	http://arxiv.org/abs/1804.03867v1
PDF	http://arxiv.org/pdf/1804.03867v1.pdf
PWC	https://paperswithcode.com/paper/hybrid-binary-networks-optimizing-for
Repo	https://github.com/erilyth/HybridBinaryNetworks-WACV18
Framework	pytorch

Invariant Representations without Adversarial Training


Title	Invariant Representations without Adversarial Training
Authors	Daniel Moyer, Shuyang Gao, Rob Brekelmans, Greg Ver Steeg, Aram Galstyan
Abstract	Representations of data that are invariant to changes in specified factors are useful for a wide range of problems: removing potential biases in prediction problems, controlling the effects of covariates, and disentangling meaningful factors of variation. Unfortunately, learning representations that exhibit invariance to arbitrary nuisance factors yet remain useful for other tasks is challenging. Existing approaches cast the trade-off between task performance and invariance in an adversarial way, using an iterative minimax optimization. We show that adversarial training is unnecessary and sometimes counter-productive; we instead cast invariant representation learning as a single information-theoretic objective that can be directly optimized. We demonstrate that this approach matches or exceeds performance of state-of-the-art adversarial approaches for learning fair representations and for generative modeling with controllable transformations.
Tasks	Representation Learning
Published	2018-05-24
URL	https://arxiv.org/abs/1805.09458v4
PDF	https://arxiv.org/pdf/1805.09458v4.pdf
PWC	https://paperswithcode.com/paper/invariant-representations-without-adversarial
Repo	https://github.com/dcmoyer/inv-rep
Framework	tf

Hierarchical Deep Multiagent Reinforcement Learning with Temporal Abstraction


Title	Hierarchical Deep Multiagent Reinforcement Learning with Temporal Abstraction
Authors	Hongyao Tang, Jianye Hao, Tangjie Lv, Yingfeng Chen, Zongzhang Zhang, Hangtian Jia, Chunxu Ren, Yan Zheng, Zhaopeng Meng, Changjie Fan, Li Wang
Abstract	Multiagent reinforcement learning (MARL) is commonly considered to suffer from non-stationary environments and exponentially increasing policy space. It would be even more challenging when rewards are sparse and delayed over long trajectories. In this paper, we study hierarchical deep MARL in cooperative multiagent problems with sparse and delayed reward. With temporal abstraction, we decompose the problem into a hierarchy of different time scales and investigate how agents can learn high-level coordination based on the independent skills learned at the low level. Three hierarchical deep MARL architectures are proposed to learn hierarchical policies under different MARL paradigms. Besides, we propose a new experience replay mechanism to alleviate the issue of the sparse transitions at the high level of abstraction and the non-stationarity of multiagent learning. We empirically demonstrate the effectiveness of our approaches in two domains with extremely sparse feedback: (1) a variety of Multiagent Trash Collection tasks, and (2) a challenging online mobile game, i.e., Fever Basketball Defense.
Tasks
Published	2018-09-25
URL	https://arxiv.org/abs/1809.09332v2
PDF	https://arxiv.org/pdf/1809.09332v2.pdf
PWC	https://paperswithcode.com/paper/hierarchical-deep-multiagent-reinforcement
Repo	https://github.com/bluecontra/MATC_Env
Framework	none

Decorrelated Batch Normalization


Title	Decorrelated Batch Normalization
Authors	Lei Huang, Dawei Yang, Bo Lang, Jia Deng
Abstract	Batch Normalization (BN) is capable of accelerating the training of deep models by centering and scaling activations within mini-batches. In this work, we propose Decorrelated Batch Normalization (DBN), which not just centers and scales activations but whitens them. We explore multiple whitening techniques, and find that PCA whitening causes a problem we call stochastic axis swapping, which is detrimental to learning. We show that ZCA whitening does not suffer from this problem, permitting successful learning. DBN retains the desirable qualities of BN and further improves BN’s optimization efficiency and generalization ability. We design comprehensive experiments to show that DBN can improve the performance of BN on multilayer perceptrons and convolutional neural networks. Furthermore, we consistently improve the accuracy of residual networks on CIFAR-10, CIFAR-100, and ImageNet.
Tasks
Published	2018-04-23
URL	http://arxiv.org/abs/1804.08450v1
PDF	http://arxiv.org/pdf/1804.08450v1.pdf
PWC	https://paperswithcode.com/paper/decorrelated-batch-normalization
Repo	https://github.com/bhneo/DecorrelatedBN_tf
Framework	tf

CariGANs: Unpaired Photo-to-Caricature Translation


Title	CariGANs: Unpaired Photo-to-Caricature Translation
Authors	Kaidi Cao, Jing Liao, Lu Yuan
Abstract	Facial caricature is an art form of drawing faces in an exaggerated way to convey humor or sarcasm. In this paper, we propose the first Generative Adversarial Network (GAN) for unpaired photo-to-caricature translation, which we call “CariGANs”. It explicitly models geometric exaggeration and appearance stylization using two components: CariGeoGAN, which only models the geometry-to-geometry transformation from face photos to caricatures, and CariStyGAN, which transfers the style appearance from caricatures to face photos without any geometry deformation. In this way, a difficult cross-domain translation problem is decoupled into two easier tasks. The perceptual study shows that caricatures generated by our CariGANs are closer to the hand-drawn ones, and at the same time better persevere the identity, compared to state-of-the-art methods. Moreover, our CariGANs allow users to control the shape exaggeration degree and change the color/texture style by tuning the parameters or giving an example caricature.
Tasks	Caricature, Photo-To-Caricature Translation
Published	2018-11-01
URL	http://arxiv.org/abs/1811.00222v2
PDF	http://arxiv.org/pdf/1811.00222v2.pdf
PWC	https://paperswithcode.com/paper/carigans-unpaired-photo-to-caricature
Repo	https://github.com/SerialLain3170/ComputerVision-Papers
Framework	none

SQL-to-Text Generation with Graph-to-Sequence Model


Title	SQL-to-Text Generation with Graph-to-Sequence Model
Authors	Kun Xu, Lingfei Wu, Zhiguo Wang, Yansong Feng, Vadim Sheinin
Abstract	Previous work approaches the SQL-to-text generation task using vanilla Seq2Seq models, which may not fully capture the inherent graph-structured information in SQL query. In this paper, we first introduce a strategy to represent the SQL query as a directed graph and then employ a graph-to-sequence model to encode the global structure information into node embeddings. This model can effectively learn the correlation between the SQL query pattern and its interpretation. Experimental results on the WikiSQL dataset and Stackoverflow dataset show that our model significantly outperforms the Seq2Seq and Tree2Seq baselines, achieving the state-of-the-art performance.
Tasks	Graph-to-Sequence, SQL-to-Text, Text Generation
Published	2018-09-14
URL	http://arxiv.org/abs/1809.05255v2
PDF	http://arxiv.org/pdf/1809.05255v2.pdf
PWC	https://paperswithcode.com/paper/sql-to-text-generation-with-graph-to-sequence
Repo	https://github.com/IBM/SQL-to-Text
Framework	tf

Arc-support Line Segments Revisited: An Efficient and High-quality Ellipse Detection


Title	Arc-support Line Segments Revisited: An Efficient and High-quality Ellipse Detection
Authors	Changsheng Lu, Siyu Xia, Ming Shao, Yun Fu
Abstract	Over the years many ellipse detection algorithms spring up and are studied broadly, while the critical issue of detecting ellipses accurately and efficiently in real-world images remains a challenge. In this paper, we propose a valuable industry-oriented ellipse detector by arc-support line segments, which simultaneously reaches high detection accuracy and efficiency. To simplify the complicated curves in an image while retaining the general properties including convexity and polarity, the arc-support line segments are extracted, which grounds the successful detection of ellipses. The arc-support groups are formed by iteratively and robustly linking the arc-support line segments that latently belong to a common ellipse. Afterward, two complementary approaches, namely, locally selecting the arc-support group with higher saliency and globally searching all the valid paired groups, are adopted to fit the initial ellipses in a fast way. Then, the ellipse candidate set can be formulated by hierarchical clustering of 5D parameter space of initial ellipses. Finally, the salient ellipse candidates are selected and refined as detections subject to the stringent and effective verification. Extensive experiments on three public datasets are implemented and our method achieves the best F-measure scores compared to the state-of-the-art methods. The source code is available at https://github.com/AlanLuSun/High-quality-ellipse-detection.
Tasks
Published	2018-10-08
URL	https://arxiv.org/abs/1810.03243v5
PDF	https://arxiv.org/pdf/1810.03243v5.pdf
PWC	https://paperswithcode.com/paper/arc-support-line-segments-revisited-an
Repo	https://github.com/AlanLuSun/High-quality-ellipse-detection
Framework	none

ServeNet: A Deep Neural Network for Web Service Classification


Title	ServeNet: A Deep Neural Network for Web Service Classification
Authors	Yilong Yang, Wei Ke, Peng Liu, Weiru Wang, Bingqing Shen, Bo Liu, Yongxin Zhao
Abstract	Automated service classification plays a crucial role in service discovery, selection, and composition. Machine learning has been used for service classification in recent years. However, the performance of conventional machine learning methods highly depends on the quality of manual feature engineering. In this paper, we present a deep neural network to automatically abstract low-level representation of service description to high-level features without feature engineering and then predict service classification on 50 service categories. To demonstrate the effectiveness of our approach, we conduct a comprehensive experimental study by comparing 10 machine learning methods on 10,000 real-world web services. The result shows that the proposed deep neural network can achieve higher accuracy than other machine learning methods.
Tasks	Feature Engineering
Published	2018-06-14
URL	https://arxiv.org/abs/1806.05437v2
PDF	https://arxiv.org/pdf/1806.05437v2.pdf
PWC	https://paperswithcode.com/paper/servenet-a-deep-neural-network-for-web
Repo	https://github.com/yylonly/ServeNet
Framework	none