January 29, 2020

3149 words 15 mins read

Paper Group ANR 759

A system for generating complex physically accurate sensor images for automotive applications. Recognition of Multiple Food Items in a Single Photo for Use in a Buffet-Style Restaurant. Robust Model Predictive Shielding for Safe Reinforcement Learning with Stochastic Dynamics. BioNLP-OST 2019 RDoC Tasks: Multi-grain Neural Relevance Ranking Using T …

A system for generating complex physically accurate sensor images for automotive applications


Title	A system for generating complex physically accurate sensor images for automotive applications
Authors	Zhenyi Liu, Minghao Shen, Jiaqi Zhang, Shuangting Liu, Henryk Blasinski, Trisha Lian, Brian Wandell
Abstract	We describe an open-source simulator that creates sensor irradiance and sensor images of typical automotive scenes in urban settings. The purpose of the system is to support camera design and testing for automotive applications. The user can specify scene parameters (e.g., scene type, road type, traffic density, time of day) to assemble a large number of random scenes from graphics assets stored in a database. The sensor irradiance is generated using quantitative computer graphics methods, and the sensor images are created using image systems sensor simulation. The synthetic sensor images have pixel level annotations; hence, they can be used to train and evaluate neural networks for imaging tasks, such as object detection and classification. The end-to-end simulation system supports quantitative assessment, from scene to camera to network accuracy, for automotive applications.
Tasks	Object Detection
Published	2019-02-12
URL	http://arxiv.org/abs/1902.04258v1
PDF	http://arxiv.org/pdf/1902.04258v1.pdf
PWC	https://paperswithcode.com/paper/a-system-for-generating-complex-physically
Repo
Framework

Recognition of Multiple Food Items in a Single Photo for Use in a Buffet-Style Restaurant


Title	Recognition of Multiple Food Items in a Single Photo for Use in a Buffet-Style Restaurant
Authors	Masashi Anzawa, Sosuke Amano, Yoko Yamakata, Keiko Motonaga, Akiko Kamei, Kiyoharu Aizawa
Abstract	We investigate image recognition of multiple food items in a single photo, focusing on a buffet restaurant application, where menu changes at every meal, and only a few images per class are available. After detecting food areas, we perform hierarchical recognition. We evaluate our results, comparing to two baseline methods.
Tasks
Published	2019-03-03
URL	http://arxiv.org/abs/1903.00858v1
PDF	http://arxiv.org/pdf/1903.00858v1.pdf
PWC	https://paperswithcode.com/paper/recognition-of-multiple-food-items-in-a
Repo
Framework

Robust Model Predictive Shielding for Safe Reinforcement Learning with Stochastic Dynamics


Title	Robust Model Predictive Shielding for Safe Reinforcement Learning with Stochastic Dynamics
Authors	Shuo Li, Osbert Bastani
Abstract	This paper proposes a framework for safe reinforcement learning that can handle stochastic nonlinear dynamical systems. We focus on the setting where the nominal dynamics are known, and are subject to additive stochastic disturbances with known distribution. Our goal is to ensure the safety of a control policy trained using reinforcement learning, e.g., in a simulated environment. We build on the idea of model predictive shielding (MPS), where a backup controller is used to override the learned policy as needed to ensure safety. The key challenge is how to compute a backup policy in the context of stochastic dynamics. We propose to use a tube-based robust NMPC controller as the backup controller. We estimate the tubes using sampled trajectories, leveraging ideas from statistical learning theory to obtain high-probability guarantees. We empirically demonstrate that our approach can ensure safety in stochastic systems, including cart-pole and a non-holonomic particle with random obstacles.
Tasks
Published	2019-10-24
URL	https://arxiv.org/abs/1910.10885v2
PDF	https://arxiv.org/pdf/1910.10885v2.pdf
PWC	https://paperswithcode.com/paper/robust-model-predictive-shielding-for-safe
Repo
Framework

BioNLP-OST 2019 RDoC Tasks: Multi-grain Neural Relevance Ranking Using Topics and Attention Based Query-Document-Sentence Interactions


Title	BioNLP-OST 2019 RDoC Tasks: Multi-grain Neural Relevance Ranking Using Topics and Attention Based Query-Document-Sentence Interactions
Authors	Yatin Chaudhary, Pankaj Gupta, Hinrich Schütze
Abstract	This paper presents our system details and results of participation in the RDoC Tasks of BioNLP-OST 2019. Research Domain Criteria (RDoC) construct is a multi-dimensional and broad framework to describe mental health disorders by combining knowledge from genomics to behaviour. Non-availability of RDoC labelled dataset and tedious labelling process hinders the use of RDoC framework to reach its full potential in Biomedical research community and Healthcare industry. Therefore, Task-1 aims at retrieval and ranking of PubMed abstracts relevant to a given RDoC construct and Task-2 aims at extraction of the most relevant sentence from a given PubMed abstract. We investigate (1) attention based supervised neural topic model and SVM for retrieval and ranking of PubMed abstracts and, further utilize BM25 and other relevance measures for re-ranking, (2) supervised and unsupervised sentence ranking models utilizing multi-view representations comprising of query-aware attention-based sentence representation (QAR), bag-of-words (BoW) and TF-IDF. Our best systems achieved 1st rank and scored 0.86 mean average precision (mAP) and 0.58 macro average accuracy (MAA) in Task-1 and Task-2 respectively.
Tasks
Published	2019-10-01
URL	https://arxiv.org/abs/1910.00314v2
PDF	https://arxiv.org/pdf/1910.00314v2.pdf
PWC	https://paperswithcode.com/paper/bionlp-ost-2019-rdoc-tasks-multi-grain-neural
Repo
Framework

Dynamic Joint Variational Graph Autoencoders


Title	Dynamic Joint Variational Graph Autoencoders
Authors	Sedigheh Mahdavi, Shima Khoshraftar, Aijun An
Abstract	Learning network representations is a fundamental task for many graph applications such as link prediction, node classification, graph clustering, and graph visualization. Many real-world networks are interpreted as dynamic networks and evolve over time. Most existing graph embedding algorithms were developed for static graphs mainly and cannot capture the evolution of a large dynamic network. In this paper, we propose Dynamic joint Variational Graph Autoencoders (Dyn-VGAE) that can learn both local structures and temporal evolutionary patterns in a dynamic network. Dyn-VGAE provides a joint learning framework for computing temporal representations of all graph snapshots simultaneously. Each auto-encoder embeds a graph snapshot based on its local structure and can also learn temporal dependencies by collaborating with other autoencoders. We conduct experimental studies on dynamic real-world graph datasets and the results demonstrate the effectiveness of the proposed method.
Tasks	Graph Clustering, Graph Embedding, Learning Network Representations, Link Prediction, Node Classification
Published	2019-10-04
URL	https://arxiv.org/abs/1910.01963v1
PDF	https://arxiv.org/pdf/1910.01963v1.pdf
PWC	https://paperswithcode.com/paper/dynamic-joint-variational-graph-autoencoders
Repo
Framework

Off-Policy Deep Reinforcement Learning by Bootstrapping the Covariate Shift


Title	Off-Policy Deep Reinforcement Learning by Bootstrapping the Covariate Shift
Authors	Carles Gelada, Marc G. Bellemare
Abstract	In this paper we revisit the method of off-policy corrections for reinforcement learning (COP-TD) pioneered by Hallak et al. (2017). Under this method, online updates to the value function are reweighted to avoid divergence issues typical of off-policy learning. While Hallak et al.‘s solution is appealing, it cannot easily be transferred to nonlinear function approximation. First, it requires a projection step onto the probability simplex; second, even though the operator describing the expected behavior of the off-policy learning algorithm is convergent, it is not known to be a contraction mapping, and hence, may be more unstable in practice. We address these two issues by introducing a discount factor into COP-TD. We analyze the behavior of discounted COP-TD and find it better behaved from a theoretical perspective. We also propose an alternative soft normalization penalty that can be minimized online and obviates the need for an explicit projection step. We complement our analysis with an empirical evaluation of the two techniques in an off-policy setting on the game Pong from the Atari domain where we find discounted COP-TD to be better behaved in practice than the soft normalization penalty. Finally, we perform a more extensive evaluation of discounted COP-TD in 5 games of the Atari domain, where we find performance gains for our approach.
Tasks
Published	2019-01-27
URL	http://arxiv.org/abs/1901.09455v1
PDF	http://arxiv.org/pdf/1901.09455v1.pdf
PWC	https://paperswithcode.com/paper/off-policy-deep-reinforcement-learning-by
Repo
Framework

Layout-Graph Reasoning for Fashion Landmark Detection


Title	Layout-Graph Reasoning for Fashion Landmark Detection
Authors	Weijiang Yu, Xiaodan Liang, Ke Gong, Chenhan Jiang, Nong Xiao, Liang Lin
Abstract	Detecting dense landmarks for diverse clothes, as a fundamental technique for clothes analysis, has attracted increasing research attention due to its huge application potential. However, due to the lack of modeling underlying semantic layout constraints among landmarks, prior works often detect ambiguous and structure-inconsistent landmarks of multiple overlapped clothes in one person. In this paper, we propose to seamlessly enforce structural layout relationships among landmarks on the intermediate representations via multiple stacked layout-graph reasoning layers. We define the layout-graph as a hierarchical structure including a root node, body-part nodes (e.g. upper body, lower body), coarse clothes-part nodes (e.g. collar, sleeve) and leaf landmark nodes (e.g. left-collar, right-collar). Each Layout-Graph Reasoning(LGR) layer aims to map feature representations into structural graph nodes via a Map-to-Node module, performs reasoning over structural graph nodes to achieve global layout coherency via a layout-graph reasoning module, and then maps graph nodes back to enhance feature representations via a Node-to-Map module. The layout-graph reasoning module integrates a graph clustering operation to generate representations of intermediate nodes (bottom-up inference) and then a graph deconvolution operation (top-down inference) over the whole graph. Extensive experiments on two public fashion landmark datasets demonstrate the superiority of our model. Furthermore, to advance the fine-grained fashion landmark research for supporting more comprehensive clothes generation and attribute recognition, we contribute the first Fine-grained Fashion Landmark Dataset (FFLD) containing 200k images annotated with at most 32 key-points for 13 clothes types.
Tasks	Graph Clustering
Published	2019-10-04
URL	https://arxiv.org/abs/1910.01923v1
PDF	https://arxiv.org/pdf/1910.01923v1.pdf
PWC	https://paperswithcode.com/paper/layout-graph-reasoning-for-fashion-landmark-1
Repo
Framework

Tree Tensor Networks for Generative Modeling


Title	Tree Tensor Networks for Generative Modeling
Authors	Song Cheng, Lei Wang, Tao Xiang, Pan Zhang
Abstract	Matrix product states (MPS), a tensor network designed for one-dimensional quantum systems, has been recently proposed for generative modeling of natural data (such as images) in terms of `Born machine’. However, the exponential decay of correlation in MPS restricts its representation power heavily for modeling complex data such as natural images. In this work, we push forward the effort of applying tensor networks to machine learning by employing the Tree Tensor Network (TTN) which exhibits balanced performance in expressibility and efficient training and sampling. We design the tree tensor network to utilize the 2-dimensional prior of the natural images and develop sweeping learning and sampling algorithms which can be efficiently implemented utilizing Graphical Processing Units (GPU). We apply our model to random binary patterns and the binary MNIST datasets of handwritten digits. We show that TTN is superior to MPS for generative modeling in keeping correlation of pixels in natural images, as well as giving better log-likelihood scores in standard datasets of handwritten digits. We also compare its performance with state-of-the-art generative models such as the Variational AutoEncoders, Restricted Boltzmann machines, and PixelCNN. Finally, we discuss the future development of Tensor Network States in machine learning problems. \|
Tasks	Tensor Networks
Published	2019-01-08
URL	http://arxiv.org/abs/1901.02217v1
PDF	http://arxiv.org/pdf/1901.02217v1.pdf
PWC	https://paperswithcode.com/paper/tree-tensor-networks-for-generative-modeling
Repo
Framework

Online Bagging for Anytime Transfer Learning


Title	Online Bagging for Anytime Transfer Learning
Authors	Guokun Chi, Min Jiang, Xing Gao, Weizhen Hu, Shihui Guo, Kay Chen Tan
Abstract	Transfer learning techniques have been widely used in the reality that it is difficult to obtain sufficient labeled data in the target domain, but a large amount of auxiliary data can be obtained in the relevant source domain. But most of the existing methods are based on offline data. In practical applications, it is often necessary to face online learning problems in which the data samples are achieved sequentially. In this paper, We are committed to applying the ensemble approach to solving the problem of online transfer learning so that it can be used in anytime setting. More specifically, we propose a novel online transfer learning framework, which applies the idea of online bagging methods to anytime transfer learning problems, and constructs strong classifiers through online iterations of the usefulness of multiple weak classifiers. Further, our algorithm also provides two extension schemes to reduce the impact of negative transfer. Experiments on three real data sets show that the effectiveness of our proposed algorithms.
Tasks	Transfer Learning
Published	2019-10-20
URL	https://arxiv.org/abs/1910.08945v1
PDF	https://arxiv.org/pdf/1910.08945v1.pdf
PWC	https://paperswithcode.com/paper/online-bagging-for-anytime-transfer-learning
Repo
Framework

On the relation between Loss Functions and T-Norms


Title	On the relation between Loss Functions and T-Norms
Authors	Francesco Giannini, Giuseppe Marra, Michelangelo Diligenti, Marco Maggini, Marco Gori
Abstract	Deep learning has been shown to achieve impressive results in several domains like computer vision and natural language processing. A key element of this success has been the development of new loss functions, like the popular cross-entropy loss, which has been shown to provide faster convergence and to reduce the vanishing gradient problem in very deep structures. While the cross-entropy loss is usually justified from a probabilistic perspective, this paper shows an alternative and more direct interpretation of this loss in terms of t-norms and their associated generator functions, and derives a general relation between loss functions and t-norms. In particular, the presented work shows intriguing results leading to the development of a novel class of loss functions. These losses can be exploited in any supervised learning task and which could lead to faster convergence rates that the commonly employed cross-entropy loss.
Tasks
Published	2019-07-18
URL	https://arxiv.org/abs/1907.07904v1
PDF	https://arxiv.org/pdf/1907.07904v1.pdf
PWC	https://paperswithcode.com/paper/on-the-relation-between-loss-functions-and-t
Repo
Framework

Graph-Based Offline Signature Verification


Title	Graph-Based Offline Signature Verification
Authors	Paul Maergner, Nicholas R. Howe, Kaspar Riesen, Rolf Ingold, Andreas Fischer
Abstract	Graphs provide a powerful representation formalism that offers great promise to benefit tasks like handwritten signature verification. While most state-of-the-art approaches to signature verification rely on fixed-size representations, graphs are flexible in size and allow modeling local features as well as the global structure of the handwriting. In this article, we present two recent graph-based approaches to offline signature verification: keypoint graphs with approximated graph edit distance and inkball models. We provide a comprehensive description of the methods, propose improvements both in terms of computational time and accuracy, and report experimental results for four benchmark datasets. The proposed methods achieve top results for several benchmarks, highlighting the potential of graph-based signature verification.
Tasks
Published	2019-06-25
URL	https://arxiv.org/abs/1906.10401v1
PDF	https://arxiv.org/pdf/1906.10401v1.pdf
PWC	https://paperswithcode.com/paper/graph-based-offline-signature-verification
Repo
Framework

Predicting Alzheimer’s Disease by Hierarchical Graph Convolution from Positron Emission Tomography Imaging


Title	Predicting Alzheimer’s Disease by Hierarchical Graph Convolution from Positron Emission Tomography Imaging
Authors	Jiaming Guo, Wei Qiu, Xiang Li, Xuandong Zhao, Ning Guo, Quanzheng Li
Abstract	Imaging-based early diagnosis of Alzheimer Disease (AD) has become an effective approach, especially by using nuclear medicine imaging techniques such as Positron Emission Topography (PET). In various literature it has been found that PET images can be better modeled as signals (e.g. uptake of florbetapir) defined on a network (non-Euclidean) structure which is governed by its underlying graph patterns of pathological progression and metabolic connectivity. In order to effectively apply deep learning framework for PET image analysis to overcome its limitation on Euclidean grid, we develop a solution for 3D PET image representation and analysis under a generalized, graph-based CNN architecture (PETNet), which analyzes PET signals defined on a group-wise inferred graph structure. Computations in PETNet are defined in non-Euclidean, graph (network) domain, as it performs feature extraction by convolution operations on spectral-filtered signals on the graph and pooling operations based on hierarchical graph clustering. Effectiveness of the PETNet is evaluated on the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset, which shows improved performance over both deep learning and other machine learning-based methods.
Tasks	Graph Clustering
Published	2019-10-01
URL	https://arxiv.org/abs/1910.00185v1
PDF	https://arxiv.org/pdf/1910.00185v1.pdf
PWC	https://paperswithcode.com/paper/predicting-alzheimers-disease-by-hierarchical
Repo
Framework

Systematic Overestimation of Machine Learning Performance in Neuroimaging Studies of Depression


Title	Systematic Overestimation of Machine Learning Performance in Neuroimaging Studies of Depression
Authors	Claas Flint, Micah Cearns, Nils Opel, Ronny Redlich, David M. A. Mehler, Daniel Emden, Nils R. Winter, Ramona Leenings, Simon B. Eickhoff, Tilo Kircher, Axel Krug, Igor Nenadic, Volker Arolt, Scott Clark, Bernhard T. Baune, Xiaoyi Jiang, Udo Dannlowski, Tim Hahn
Abstract	We currently observe a disconcerting phenomenon in machine learning studies in psychiatry: While we would expect larger samples to yield better results due to the availability of more data, larger machine learning studies consistently show much weaker performance than the numerous small-scale studies. Here, we systematically investigated this effect focusing on one of the most heavily studied questions in the field, namely the classification of patients suffering from Major Depressive Disorder (MDD) and healthy controls. Drawing upon a balanced sample of $N = 1,868$ MDD patients and healthy controls from our recent international Predictive Analytics Competition (PAC), we first trained and tested a classification model on the full dataset which yielded an accuracy of 61%. Next, we mimicked the process by which researchers would draw samples of various sizes ($N=4$ to $N=150$) from the population and showed a strong risk of overestimation. Specifically, for small sample sizes ($N=20$), we observe accuracies of up to 95%. For medium sample sizes ($N=100$) accuracies up to 75% were found. Importantly, further investigation showed that sufficiently large test sets effectively protect against performance overestimation whereas larger datasets per se do not. While these results question the validity of a substantial part of the current literature, we outline the relatively low-cost remedy of larger test sets.
Tasks
Published	2019-12-13
URL	https://arxiv.org/abs/1912.06686v1
PDF	https://arxiv.org/pdf/1912.06686v1.pdf
PWC	https://paperswithcode.com/paper/systematic-overestimation-of-machine-learning
Repo
Framework

Affective Behaviour Analysis of On-line User Interactions: Are On-line Support Groups more Therapeutic than Twitter?


Title	Affective Behaviour Analysis of On-line User Interactions: Are On-line Support Groups more Therapeutic than Twitter?
Authors	Giuliano Tortoreto, Evgeny A. Stepanov, Alessandra Cervone, Mateusz Dubiel, Giuseppe Riccardi
Abstract	The increase in the prevalence of mental health problems has coincided with a growing popularity of health related social networking sites. Regardless of their therapeutic potential, On-line Support Groups (OSGs) can also have negative effects on patients. In this work we propose a novel methodology to automatically verify the presence of therapeutic factors in social networking websites by using Natural Language Processing (NLP) techniques. The methodology is evaluated on On-line asynchronous multi-party conversations collected from an OSG and Twitter. The results of the analysis indicate that therapeutic factors occur more frequently in OSG conversations than in Twitter conversations. Moreover, the analysis of OSG conversations reveals that the users of that platform are supportive, and interactions are likely to lead to the improvement of their emotional state. We believe that our method provides a stepping stone towards automatic analysis of emotional states of users of online platforms. Possible applications of the method include provision of guidelines that highlight potential implications of using such platforms on users’ mental health, and/or support in the analysis of their impact on specific individuals.
Tasks
Published	2019-11-04
URL	https://arxiv.org/abs/1911.01371v1
PDF	https://arxiv.org/pdf/1911.01371v1.pdf
PWC	https://paperswithcode.com/paper/affective-behaviour-analysis-of-on-line-user-1
Repo
Framework

Domain Adaptation for Object Detection via Style Consistency


Title	Domain Adaptation for Object Detection via Style Consistency
Authors	Adrian Lopez Rodriguez, Krystian Mikolajczyk
Abstract	We propose a domain adaptation approach for object detection. We introduce a two-step method: the first step makes the detector robust to low-level differences and the second step adapts the classifiers to changes in the high-level features. For the first step, we use a style transfer method for pixel-adaptation of source images to the target domain. We find that enforcing low distance in the high-level features of the object detector between the style transferred images and the source images improves the performance in the target domain. For the second step, we propose a robust pseudo labelling approach to reduce the noise in both positive and negative sampling. Experimental evaluation is performed using the detector SSD300 on PASCAL VOC extended with the dataset proposed in arxiv:1803.11365 where the target domain images are of different styles. Our approach significantly improves the state-of-the-art performance in this benchmark.
Tasks	Domain Adaptation, Object Detection, Style Transfer
Published	2019-11-22
URL	https://arxiv.org/abs/1911.10033v1
PDF	https://arxiv.org/pdf/1911.10033v1.pdf
PWC	https://paperswithcode.com/paper/domain-adaptation-for-object-detection-via
Repo
Framework