April 1, 2020

3171 words 15 mins read

Paper Group ANR 442

Fast Detection of Maximum Common Subgraph via Deep Q-Learning. Semi-supervised Anomaly Detection using AutoEncoders. Rough Set based Aggregate Rank Measure & its Application to Supervised Multi Document Summarization. An Exploration of Embodied Visual Exploration. StereoNeuroBayesSLAM: A Neurobiologically Inspired Stereo Visual SLAM System Based on …

Fast Detection of Maximum Common Subgraph via Deep Q-Learning


Title	Fast Detection of Maximum Common Subgraph via Deep Q-Learning
Authors	Yunsheng Bai, Derek Xu, Alex Wang, Ken Gu, Xueqing Wu, Agustin Marinovic, Christopher Ro, Yizhou Sun, Wei Wang
Abstract	Detecting the Maximum Common Subgraph (MCS) between two input graphs is fundamental for applications in biomedical analysis, malware detection, cloud computing, etc. This is especially important in the task of drug design, where the successful extraction of common substructures in compounds can reduce the number of experiments needed to be conducted by humans. However, MCS computation is NP-hard, and state-of-the-art exact MCS solvers do not have worst-case time complexity guarantee and cannot handle large graphs in practice. Designing learning based models to find the MCS between two graphs in an approximate yet accurate way while utilizing as few labeled MCS instances as possible remains to be a challenging task. Here we propose RLMCS, a Graph Neural Network based model for MCS detection through reinforcement learning. Our model uses an exploration tree to extract subgraphs in two graphs one node pair at a time, and is trained to optimize subgraph extraction rewards via Deep Q-Networks. A novel graph embedding method is proposed to generate state representations for nodes and extracted subgraphs jointly at each step. Experiments on real graph datasets demonstrate that our model performs favorably to exact MCS solvers and supervised neural graph matching network models in terms of accuracy and efficiency.
Tasks	Graph Embedding, Graph Matching, Malware Detection, Q-Learning
Published	2020-02-08
URL	https://arxiv.org/abs/2002.03129v2
PDF	https://arxiv.org/pdf/2002.03129v2.pdf
PWC	https://paperswithcode.com/paper/fast-detection-of-maximum-common-subgraph-via
Repo
Framework

Semi-supervised Anomaly Detection using AutoEncoders


Title	Semi-supervised Anomaly Detection using AutoEncoders
Authors	Manpreet Singh Minhas, John Zelek
Abstract	Anomaly detection refers to the task of finding unusual instances that stand out from the normal data. In several applications, these outliers or anomalous instances are of greater interest compared to the normal ones. Specifically in the case of industrial optical inspection and infrastructure asset management, finding these defects (anomalous regions) is of extreme importance. Traditionally and even today this process has been carried out manually. Humans rely on the saliency of the defects in comparison to the normal texture to detect the defects. However, manual inspection is slow, tedious, subjective and susceptible to human biases. Therefore, the automation of defect detection is desirable. But for defect detection lack of availability of a large number of anomalous instances and labelled data is a problem. In this paper, we present a convolutional auto-encoder architecture for anomaly detection that is trained only on the defect-free (normal) instances. For the test images, residual masks that are obtained by subtracting the original image from the auto-encoder output are thresholded to obtain the defect segmentation masks. The approach was tested on two data-sets and achieved an impressive average F1 score of 0.885. The network learnt to detect the actual shape of the defects even though no defected images were used during the training.
Tasks	Anomaly Detection
Published	2020-01-06
URL	https://arxiv.org/abs/2001.03674v1
PDF	https://arxiv.org/pdf/2001.03674v1.pdf
PWC	https://paperswithcode.com/paper/semi-supervised-anomaly-detection-using
Repo
Framework

Rough Set based Aggregate Rank Measure & its Application to Supervised Multi Document Summarization


Title	Rough Set based Aggregate Rank Measure & its Application to Supervised Multi Document Summarization
Authors	Nidhika Yadav, Niladri Chatterjee
Abstract	Most problems in Machine Learning cater to classification and the objects of universe are classified to a relevant class. Ranking of classified objects of universe per decision class is a challenging problem. We in this paper propose a novel Rough Set based membership called Rank Measure to solve to this problem. It shall be utilized for ranking the elements to a particular class. It differs from Pawlak Rough Set based membership function which gives an equivalent characterization of the Rough Set based approximations. It becomes paramount to look beyond the traditional approach of computing memberships while handling inconsistent, erroneous and missing data that is typically present in real world problems. This led us to propose the aggregate Rank Measure. The contribution of the paper is three fold. Firstly, it proposes a Rough Set based measure to be utilized for numerical characterization of within class ranking of objects. Secondly, it proposes and establish the properties of Rank Measure and aggregate Rank Measure based membership. Thirdly, we apply the concept of membership and aggregate ranking to the problem of supervised Multi Document Summarization wherein first the important class of sentences are determined using various supervised learning techniques and are post processed using the proposed ranking measure. The results proved to have significant improvement in accuracy.
Tasks	Document Summarization, Multi-Document Summarization
Published	2020-02-09
URL	https://arxiv.org/abs/2002.03259v1
PDF	https://arxiv.org/pdf/2002.03259v1.pdf
PWC	https://paperswithcode.com/paper/rough-set-based-aggregate-rank-measure-its
Repo
Framework

An Exploration of Embodied Visual Exploration


Title	An Exploration of Embodied Visual Exploration
Authors	Santhosh K. Ramakrishnan, Dinesh Jayaraman, Kristen Grauman
Abstract	Embodied computer vision considers perception for robots in general, unstructured environments. Of particular importance is the embodied visual exploration problem: how might a robot equipped with a camera scope out a new environment? Despite the progress thus far, many basic questions pertinent to this problem remain unanswered: (i) What does it mean for an agent to explore its environment well? (ii) Which methods work well, and under which assumptions and environmental settings? (iii) Where do current approaches fall short, and where might future work seek to improve? Seeking answers to these questions, we perform a thorough empirical study of four state-of-the-art paradigms on two photorealistic simulated 3D environments. We present a taxonomy of key exploration methods and a standard framework for benchmarking visual exploration algorithms. Our experimental results offer insights, and suggest new performance metrics and baselines for future work in visual exploration.
Tasks
Published	2020-01-07
URL	https://arxiv.org/abs/2001.02192v1
PDF	https://arxiv.org/pdf/2001.02192v1.pdf
PWC	https://paperswithcode.com/paper/an-exploration-of-embodied-visual-exploration
Repo
Framework

StereoNeuroBayesSLAM: A Neurobiologically Inspired Stereo Visual SLAM System Based on Direct Sparse Method


Title	StereoNeuroBayesSLAM: A Neurobiologically Inspired Stereo Visual SLAM System Based on Direct Sparse Method
Authors	Taiping Zeng, Xiaoli Li, Bailu Si
Abstract	We propose a neurobiologically inspired visual simultaneous localization and mapping (SLAM) system based on direction sparse method to real-time build cognitive maps of large-scale environments from a moving stereo camera. The core SLAM system mainly comprises a Bayesian attractor network, which utilizes neural responses of head direction (HD) cells in the hippocampus and grid cells in the medial entorhinal cortex (MEC) to represent the head direction and the position of the robot in the environment, respectively. Direct sparse method is employed to accurately and robustly estimate velocity information from a stereo camera. Input rotational and translational velocities are integrated by the HD cell and grid cell networks, respectively. We demonstrated our neurobiologically inspired stereo visual SLAM system on the KITTI odometry benchmark datasets. Our proposed SLAM system is robust to real-time build a coherent semi-metric topological map from a stereo camera. Qualitative evaluation on cognitive maps shows that our proposed neurobiologically inspired stereo visual SLAM system outperforms our previous brain-inspired algorithms and the neurobiologically inspired monocular visual SLAM system both in terms of tracking accuracy and robustness, which is closer to the traditional state-of-the-art one.
Tasks	Simultaneous Localization and Mapping
Published	2020-03-06
URL	https://arxiv.org/abs/2003.03091v1
PDF	https://arxiv.org/pdf/2003.03091v1.pdf
PWC	https://paperswithcode.com/paper/stereoneurobayesslam-a-neurobiologically
Repo
Framework

Learning Contextualized Sentence Representations for Document-Level Neural Machine Translation


Title	Learning Contextualized Sentence Representations for Document-Level Neural Machine Translation
Authors	Pei Zhang, Xu Zhang, Wei Chen, Jian Yu, Yanfeng Wang, Deyi Xiong
Abstract	Document-level machine translation incorporates inter-sentential dependencies into the translation of a source sentence. In this paper, we propose a new framework to model cross-sentence dependencies by training neural machine translation (NMT) to predict both the target translation and surrounding sentences of a source sentence. By enforcing the NMT model to predict source context, we want the model to learn “contextualized” source sentence representations that capture document-level dependencies on the source side. We further propose two different methods to learn and integrate such contextualized sentence embeddings into NMT: a joint training method that jointly trains an NMT model with the source context prediction model and a pre-training & fine-tuning method that pretrains the source context prediction model on a large-scale monolingual document corpus and then fine-tunes it with the NMT model. Experiments on Chinese-English and English-German translation show that both methods can substantially improve the translation quality over a strong document-level Transformer baseline.
Tasks	Machine Translation, Sentence Embeddings
Published	2020-03-30
URL	https://arxiv.org/abs/2003.13205v1
PDF	https://arxiv.org/pdf/2003.13205v1.pdf
PWC	https://paperswithcode.com/paper/learning-contextualized-sentence
Repo
Framework

Learning Interactions and Relationships between Movie Characters


Title	Learning Interactions and Relationships between Movie Characters
Authors	Anna Kukleva, Makarand Tapaswi, Ivan Laptev
Abstract	Interactions between people are often governed by their relationships. On the flip side, social relationships are built upon several interactions. Two strangers are more likely to greet and introduce themselves while becoming friends over time. We are fascinated by this interplay between interactions and relationships, and believe that it is an important aspect of understanding social situations. In this work, we propose neural models to learn and jointly predict interactions, relationships, and the pair of characters that are involved. We note that interactions are informed by a mixture of visual and dialog cues, and present a multimodal architecture to extract meaningful information from them. Localizing the pair of interacting characters in video is a time-consuming process, instead, we train our model to learn from clip-level weak labels. We evaluate our models on the MovieGraphs dataset and show the impact of modalities, use of longer temporal context for predicting relationships, and achieve encouraging performance using weak labels as compared with ground-truth labels. Code is online.
Tasks
Published	2020-03-29
URL	https://arxiv.org/abs/2003.13158v1
PDF	https://arxiv.org/pdf/2003.13158v1.pdf
PWC	https://paperswithcode.com/paper/learning-interactions-and-relationships
Repo
Framework

Wireless Power Control via Counterfactual Optimization of Graph Neural Networks


Title	Wireless Power Control via Counterfactual Optimization of Graph Neural Networks
Authors	Navid Naderializadeh, Mark Eisen, Alejandro Ribeiro
Abstract	We consider the problem of downlink power control in wireless networks, consisting of multiple transmitter-receiver pairs communicating with each other over a single shared wireless medium. To mitigate the interference among concurrent transmissions, we leverage the network topology to create a graph neural network architecture, and we then use an unsupervised primal-dual counterfactual optimization approach to learn optimal power allocation decisions. We show how the counterfactual optimization technique allows us to guarantee a minimum rate constraint, which adapts to the network size, hence achieving the right balance between average and $5^{th}$ percentile user rates throughout a range of network configurations.
Tasks
Published	2020-02-17
URL	https://arxiv.org/abs/2002.07631v1
PDF	https://arxiv.org/pdf/2002.07631v1.pdf
PWC	https://paperswithcode.com/paper/wireless-power-control-via-counterfactual
Repo
Framework

On the Importance of Word Order Information in Cross-lingual Sequence Labeling


Title	On the Importance of Word Order Information in Cross-lingual Sequence Labeling
Authors	Zihan Liu, Genta Indra Winata, Samuel Cahyawijaya, Andrea Madotto, Zhaojiang Lin, Pascale Fung
Abstract	Word order variances generally exist in different languages. In this paper, we hypothesize that cross-lingual models that fit into the word order of the source language might fail to handle target languages. To verify this hypothesis, we investigate whether making models insensitive to the word order of the source language can improve the adaptation performance in target languages. To do so, we reduce the source language word order information fitted to sequence encoders and observe the performance changes. In addition, based on this hypothesis, we propose a new method for fine-tuning multilingual BERT in downstream cross-lingual sequence labeling tasks. Experimental results on dialogue natural language understanding, part-of-speech tagging, and named entity recognition tasks show that reducing word order information fitted to the model can achieve better zero-shot cross-lingual performance. Furthermore, our proposed methods can also be applied to strong cross-lingual baselines, and improve their performances.
Tasks	Named Entity Recognition, Part-Of-Speech Tagging
Published	2020-01-30
URL	https://arxiv.org/abs/2001.11164v3
PDF	https://arxiv.org/pdf/2001.11164v3.pdf
PWC	https://paperswithcode.com/paper/do-we-need-word-order-information-for-cross
Repo
Framework

Learning to Control PDEs with Differentiable Physics


Title	Learning to Control PDEs with Differentiable Physics
Authors	Philipp Holl, Vladlen Koltun, Nils Thuerey
Abstract	Predicting outcomes and planning interactions with the physical world are long-standing goals for machine learning. A variety of such tasks involves continuous physical systems, which can be described by partial differential equations (PDEs) with many degrees of freedom. Existing methods that aim to control the dynamics of such systems are typically limited to relatively short time frames or a small number of interaction parameters. We present a novel hierarchical predictor-corrector scheme which enables neural networks to learn to understand and control complex nonlinear physical systems over long time frames. We propose to split the problem into two distinct tasks: planning and control. To this end, we introduce a predictor network that plans optimal trajectories and a control network that infers the corresponding control parameters. Both stages are trained end-to-end using a differentiable PDE solver. We demonstrate that our method successfully develops an understanding of complex physical systems and learns to control them for tasks involving PDEs such as the incompressible Navier-Stokes equations.
Tasks
Published	2020-01-21
URL	https://arxiv.org/abs/2001.07457v1
PDF	https://arxiv.org/pdf/2001.07457v1.pdf
PWC	https://paperswithcode.com/paper/learning-to-control-pdes-with-differentiable-1
Repo
Framework

Facial Affect Recognition in the Wild Using Multi-Task Learning Convolutional Network


Title	Facial Affect Recognition in the Wild Using Multi-Task Learning Convolutional Network
Authors	Zihang Zhang, Jianping Gu
Abstract	This paper presents a neural network based method Multi-Task Affect Net(MTANet) submitted to the Affective Behavior Analysis in-the-Wild Challenge in FG2020. This method is a multi-task network and based on SE-ResNet modules. By utilizing multi-task learning, this network can estimate and recognize three quantified affective models: valence and arousal, action units, and seven basic emotions simultaneously. MTANet achieve Concordance Correlation Coefficient(CCC) rates of 0.28 and 0.34 for valence and arousal, F1-score of 0.427 and 0.32 for AUs detection and categorical emotion classification.
Tasks	Emotion Classification, Multi-Task Learning
Published	2020-02-03
URL	https://arxiv.org/abs/2002.00606v1
PDF	https://arxiv.org/pdf/2002.00606v1.pdf
PWC	https://paperswithcode.com/paper/facial-affect-recognition-in-the-wild-using
Repo
Framework

Kullback-Leibler Divergence-Based Fuzzy $C$-Means Clustering Incorporating Morphological Reconstruction and Wavelet Frames for Image Segmentation


Title	Kullback-Leibler Divergence-Based Fuzzy $C$-Means Clustering Incorporating Morphological Reconstruction and Wavelet Frames for Image Segmentation
Authors	Cong Wang, Witold Pedrycz, ZhiWu Li, MengChu Zhou
Abstract	Although spatial information of images usually enhance the robustness of the Fuzzy C-Means (FCM) algorithm, it greatly increases the computational costs for image segmentation. To achieve a sound trade-off between the segmentation performance and the speed of clustering, we come up with a Kullback-Leibler (KL) divergence-based FCM algorithm by incorporating a tight wavelet frame transform and a morphological reconstruction operation. To enhance FCM’s robustness, an observed image is first filtered by using the morphological reconstruction. A tight wavelet frame system is employed to decompose the observed and filtered images so as to form their feature sets. Considering these feature sets as data of clustering, an modified FCM algorithm is proposed, which introduces a KL divergence term in the partition matrix into its objective function. The KL divergence term aims to make membership degrees of each image pixel closer to those of its neighbors, which brings that the membership partition becomes more suitable and the parameter setting of FCM becomes simplified. On the basis of the obtained partition matrix and prototypes, the segmented feature set is reconstructed by minimizing the inverse process of the modified objective function. To modify abnormal features produced in the reconstruction process, each reconstructed feature is reassigned to the closest prototype. As a result, the segmentation accuracy of KL divergence-based FCM is further improved. What’s more, the segmented image is reconstructed by using a tight wavelet frame reconstruction operation. Finally, supporting experiments coping with synthetic, medical and color images are reported. Experimental results exhibit that the proposed algorithm works well and comes with better segmentation performance than other comparative algorithms. Moreover, the proposed algorithm requires less time than most of the FCM-related algorithms.
Tasks	Semantic Segmentation
Published	2020-02-21
URL	https://arxiv.org/abs/2002.09479v1
PDF	https://arxiv.org/pdf/2002.09479v1.pdf
PWC	https://paperswithcode.com/paper/kullback-leibler-divergence-based-fuzzy-c
Repo
Framework

Optimistic Policy Optimization with Bandit Feedback


Title	Optimistic Policy Optimization with Bandit Feedback
Authors	Yonathan Efroni, Lior Shani, Aviv Rosenberg, Shie Mannor
Abstract	Policy optimization methods are one of the most widely used classes of Reinforcement Learning (RL) algorithms. Yet, so far, such methods have been mostly analyzed from an optimization perspective, without addressing the problem of exploration, or by making strong assumptions on the interaction with the environment. In this paper we consider model-based RL in the tabular finite-horizon MDP setting with unknown transitions and bandit feedback. For this setting, we propose an optimistic trust region policy optimization (TRPO) algorithm for which we establish $\tilde O(\sqrt{S^2 A H^4 K})$ regret for stochastic rewards. Furthermore, we prove $\tilde O( \sqrt{ S^2 A H^4 } K^{2/3} ) $ regret for adversarial rewards. Interestingly, this result matches previous bounds derived for the bandit feedback case, yet with known transitions. To the best of our knowledge, the two results are the first sub-linear regret bounds obtained for policy optimization algorithms with unknown transitions and bandit feedback.
Tasks
Published	2020-02-19
URL	https://arxiv.org/abs/2002.08243v1
PDF	https://arxiv.org/pdf/2002.08243v1.pdf
PWC	https://paperswithcode.com/paper/optimistic-policy-optimization-with-bandit
Repo
Framework

siaNMS: Non-Maximum Suppression with Siamese Networks for Multi-Camera 3D Object Detection


Title	siaNMS: Non-Maximum Suppression with Siamese Networks for Multi-Camera 3D Object Detection
Authors	Irene Cortes, Jorge Beltran, Arturo de la Escalera, Fernando Garcia
Abstract	The rapid development of embedded hardware in autonomous vehicles broadens their computational capabilities, thus bringing the possibility to mount more complete sensor setups able to handle driving scenarios of higher complexity. As a result, new challenges such as multiple detections of the same object have to be addressed. In this work, a siamese network is integrated into the pipeline of a well-known 3D object detector approach to suppress duplicate proposals coming from different cameras via re-identification. Additionally, associations are exploited to enhance the 3D box regression of the object by aggregating their corresponding LiDAR frustums. The experimental evaluation on the nuScenes dataset shows that the proposed method outperforms traditional NMS approaches.
Tasks	3D Object Detection, Autonomous Vehicles, Object Detection
Published	2020-02-19
URL	https://arxiv.org/abs/2002.08239v1
PDF	https://arxiv.org/pdf/2002.08239v1.pdf
PWC	https://paperswithcode.com/paper/sianms-non-maximum-suppression-with-siamese
Repo
Framework

A Heteroscedastic Uncertainty Model for Decoupling Sources of MRI Image Quality


Title	A Heteroscedastic Uncertainty Model for Decoupling Sources of MRI Image Quality
Authors	Richard Shaw, Carole H. Sudre, Sebastien Ourselin, M. Jorge Cardoso
Abstract	Quality control (QC) of medical images is essential to ensure that downstream analyses such as segmentation can be performed successfully. Currently, QC is predominantly performed visually at significant time and operator cost. We aim to automate the process by formulating a probabilistic network that estimates uncertainty through a heteroscedastic noise model, hence providing a proxy measure of task-specific image quality that is learnt directly from the data. By augmenting the training data with different types of simulated k-space artefacts, we propose a novel cascading CNN architecture based on a student-teacher framework to decouple sources of uncertainty related to different k-space augmentations in an entirely self-supervised manner. This enables us to predict separate uncertainty quantities for the different types of data degradation. While the uncertainty measures reflect the presence and severity of image artefacts, the network also provides the segmentation predictions given the quality of the data. We show models trained with simulated artefacts provide informative measures of uncertainty on real-world images and we validate our uncertainty predictions on problematic images identified by human-raters.
Tasks
Published	2020-01-31
URL	https://arxiv.org/abs/2001.11927v1
PDF	https://arxiv.org/pdf/2001.11927v1.pdf
PWC	https://paperswithcode.com/paper/a-heteroscedastic-uncertainty-model-for
Repo
Framework