January 30, 2020

3202 words 16 mins read

Paper Group ANR 238

Creation and Evaluation of Datasets for Distributional Semantics Tasks in the Digital Humanities Domain. PAC-Bayes Analysis of Sentence Representation. Performance comparison of 3D correspondence grouping algorithm for 3D plant point clouds. Exploring the Role of Common Model of Cognition in Designing Adaptive Coaching Interactions for Health Behav …

Creation and Evaluation of Datasets for Distributional Semantics Tasks in the Digital Humanities Domain


Title	Creation and Evaluation of Datasets for Distributional Semantics Tasks in the Digital Humanities Domain
Authors	Gerhard Wohlgenannt, Ariadna Barinova, Dmitry Ilvovsky, Ekaterina Chernyak
Abstract	Word embeddings are already well studied in the general domain, usually trained on large text corpora, and have been evaluated for example on word similarity and analogy tasks, but also as an input to downstream NLP processes. In contrast, in this work we explore the suitability of word embedding technologies in the specialized digital humanities domain. After training embedding models of various types on two popular fantasy novel book series, we evaluate their performance on two task types: term analogies, and word intrusion. To this end, we manually construct test datasets with domain experts. Among the contributions are the evaluation of various word embedding techniques on the different task types, with the findings that even embeddings trained on small corpora perform well for example on the word intrusion task. Furthermore, we provide extensive and high-quality datasets in digital humanities for further investigation, as well as the implementation to easily reproduce or extend the experiments.
Tasks	Word Embeddings
Published	2019-03-07
URL	http://arxiv.org/abs/1903.02671v1
PDF	http://arxiv.org/pdf/1903.02671v1.pdf
PWC	https://paperswithcode.com/paper/creation-and-evaluation-of-datasets-for
Repo
Framework

PAC-Bayes Analysis of Sentence Representation


Title	PAC-Bayes Analysis of Sentence Representation
Authors	Kento Nozawa, Issei Sato
Abstract	Learning sentence vectors from an unlabeled corpus has attracted attention because such vectors can represent sentences in a lower dimensional and continuous space. Simple heuristics using pre-trained word vectors are widely applied to machine learning tasks. However, they are not well understood from a theoretical perspective. We analyze learning sentence vectors from a transfer learning perspective by using a PAC-Bayes bound that enables us to understand existing heuristics. We show that simple heuristics such as averaging and inverse document frequency weighted averaging are derived by our formulation. Moreover, we propose novel sentence vector learning algorithms on the basis of our PAC-Bayes analysis.
Tasks	Transfer Learning
Published	2019-02-12
URL	http://arxiv.org/abs/1902.04247v2
PDF	http://arxiv.org/pdf/1902.04247v2.pdf
PWC	https://paperswithcode.com/paper/pac-bayes-analysis-of-sentence-representation
Repo
Framework

Performance comparison of 3D correspondence grouping algorithm for 3D plant point clouds


Title	Performance comparison of 3D correspondence grouping algorithm for 3D plant point clouds
Authors	Shiva Azimi, Tapan K. Gandhi
Abstract	Plant Phenomics can be used to monitor the health and the growth of plants. Computer vision applications like stereo reconstruction, image retrieval, object tracking, and object recognition play an important role in imaging based plant phenotyping. This paper offers a comparative evaluation of some popular 3D correspondence grouping algorithms, motivated by the important role that they can play in tasks such as model creation, plant recognition and identifying plant parts. Another contribution of this paper is the extension of 2D maximum likelihood matching to 3D Maximum Likelihood Estimation Sample Consensus (MLEASAC). MLESAC is efficient and is computationally less intense than 3D random sample consensus (RANSAC). We test these algorithms on 3D point clouds of plants along with two standard benchmarks addressing shape retrieval and point cloud registration scenarios. The performance is evaluated in terms of precision and recall.
Tasks	Image Retrieval, Object Recognition, Object Tracking, Point Cloud Registration
Published	2019-09-02
URL	https://arxiv.org/abs/1909.00866v1
PDF	https://arxiv.org/pdf/1909.00866v1.pdf
PWC	https://paperswithcode.com/paper/performance-comparison-of-3d-correspondence
Repo
Framework

Exploring the Role of Common Model of Cognition in Designing Adaptive Coaching Interactions for Health Behavior Change


Title	Exploring the Role of Common Model of Cognition in Designing Adaptive Coaching Interactions for Health Behavior Change
Authors	Shiwali Mohan
Abstract	Our research aims to develop intelligent collaborative agents that are human-aware - they can model, learn, and reason about their human partner’s physiological, cognitive, and affective states. In this paper, we study how adaptive coaching interactions can be designed to help people develop sustainable healthy behaviors. We leverage the common model of cognition - CMC [26] - as a framework for unifying several behavior change theories that are known to be useful in human-human coaching. We motivate a set of interactive system desiderata based on the CMC-based view of behavior change. Then, we propose PARCoach - an interactive system that addresses the desiderata. PARCoach helps a trainee pick a relevant health goal, set an implementation intention, and track their behavior. During this process, the trainee identifies a specific goal-directed behavior as well as the situational context in which they will perform it. PARCcoach uses this information to send notifications to the trainee, reminding them of their chosen behavior and the context. We report the results from a 4-week deployment with 60 participants. Our results support the CMC-based view of behavior change and demonstrate that the desiderata for proposed interactive system design is useful in producing behavior change.
Tasks
Published	2019-10-17
URL	https://arxiv.org/abs/1910.07728v2
PDF	https://arxiv.org/pdf/1910.07728v2.pdf
PWC	https://paperswithcode.com/paper/exploring-the-role-of-common-model-of
Repo
Framework

Exploring the effects of Lx-norm penalty terms in multivariate curve resolution methods for resolving LC/GC-MS data


Title	Exploring the effects of Lx-norm penalty terms in multivariate curve resolution methods for resolving LC/GC-MS data
Authors	Ahmad Mani-Varnosfaderani, Mohammad Javad Masroor
Abstract	There are different problems for resolution of complex LC-MS or GC-MS data, such as the existence of embedded chromatographic peaks, continuum background and overlapping in mass channels for different components. These problems cause rotational ambiguity in recovered profiles calculated using multivariate curve resolution (MCR) methods. Since mass spectra are sparse in nature, sparsity has been proposed recently as a constraint in MCR methods for analyzing LC-MS data. There are different ways for implementation of the sparsity constraint, and majority of methods rely on imposing a penalty based on the L0-, L1- and L2-norms of recovered mass spectra. Ridge regression and least absolute shrinkage and selection operator (Lasso) can be used for implementation of L2- and L1-norm penalties in MCR, respectively. The main question is which Lx-norm penalty is more worthwhile for implementation of the sparsity constraint in MCR methods. In order to address this question, two and three component LC-MS data were simulated and used for the case study in this work. The areas of feasible solutions (AFS) were calculated using the grid search strategy. Calculating Lx-norms values in AFS for x between zero and two revealed that the gradient of optimization surface increased from x values equal to two to x values near zero. However, for x equal to zero, the optimization surface was similar to a plateau, which increased the risk of sticking in local minima. Generally, results in this work, recommend the use of L1-norm penalty methods like Lasso for implementation of sparsity constraint in MCR-ALS algorithm for finding more sparse solutions and reducing the extent of rotational ambiguity.
Tasks
Published	2019-05-21
URL	https://arxiv.org/abs/1905.08575v1
PDF	https://arxiv.org/pdf/1905.08575v1.pdf
PWC	https://paperswithcode.com/paper/exploring-the-effects-of-lx-norm-penalty
Repo
Framework

The Impact of Regularization on High-dimensional Logistic Regression


Title	The Impact of Regularization on High-dimensional Logistic Regression
Authors	Fariborz Salehi, Ehsan Abbasi, Babak Hassibi
Abstract	Logistic regression is commonly used for modeling dichotomous outcomes. In the classical setting, where the number of observations is much larger than the number of parameters, properties of the maximum likelihood estimator in logistic regression are well understood. Recently, Sur and Candes have studied logistic regression in the high-dimensional regime, where the number of observations and parameters are comparable, and show, among other things, that the maximum likelihood estimator is biased. In the high-dimensional regime the underlying parameter vector is often structured (sparse, block-sparse, finite-alphabet, etc.) and so in this paper we study regularized logistic regression (RLR), where a convex regularizer that encourages the desired structure is added to the negative of the log-likelihood function. An advantage of RLR is that it allows parameter recovery even for instances where the (unconstrained) maximum likelihood estimate does not exist. We provide a precise analysis of the performance of RLR via the solution of a system of six nonlinear equations, through which any performance metric of interest (mean, mean-squared error, probability of support recovery, etc.) can be explicitly computed. Our results generalize those of Sur and Candes and we provide a detailed study for the cases of $\ell_2^2$-RLR and sparse ($\ell_1$-regularized) logistic regression. In both cases, we obtain explicit expressions for various performance metrics and can find the values of the regularizer parameter that optimizes the desired performance. The theory is validated by extensive numerical simulations across a range of parameter values and problem instances.
Tasks
Published	2019-06-10
URL	https://arxiv.org/abs/1906.03761v4
PDF	https://arxiv.org/pdf/1906.03761v4.pdf
PWC	https://paperswithcode.com/paper/the-impact-of-regularization-on-high
Repo
Framework

FreiHAND: A Dataset for Markerless Capture of Hand Pose and Shape from Single RGB Images


Title	FreiHAND: A Dataset for Markerless Capture of Hand Pose and Shape from Single RGB Images
Authors	Christian Zimmermann, Duygu Ceylan, Jimei Yang, Bryan Russell, Max Argus, Thomas Brox
Abstract	Estimating 3D hand pose from single RGB images is a highly ambiguous problem that relies on an unbiased training dataset. In this paper, we analyze cross-dataset generalization when training on existing datasets. We find that approaches perform well on the datasets they are trained on, but do not generalize to other datasets or in-the-wild scenarios. As a consequence, we introduce the first large-scale, multi-view hand dataset that is accompanied by both 3D hand pose and shape annotations. For annotating this real-world dataset, we propose an iterative, semi-automated `human-in-the-loop’ approach, which includes hand fitting optimization to infer both the 3D pose and shape for each sample. We show that methods trained on our dataset consistently perform well when tested on other datasets. Moreover, the dataset allows us to train a network that predicts the full articulated hand shape from a single RGB image. The evaluation set can serve as a benchmark for articulated hand shape estimation. \|
Tasks
Published	2019-09-10
URL	https://arxiv.org/abs/1909.04349v3
PDF	https://arxiv.org/pdf/1909.04349v3.pdf
PWC	https://paperswithcode.com/paper/freihand-a-dataset-for-markerless-capture-of
Repo
Framework

Foolproof Cooperative Learning


Title	Foolproof Cooperative Learning
Authors	Alexis Jacq, Julien Perolat, Matthieu Geist, Olivier Pietquin
Abstract	This paper extends the notion of learning equilibrium in game theory from matrix games to stochastic games. We introduce Foolproof Cooperative Learning (FCL), an algorithm that converges to a Tit-for-Tat behavior. It allows cooperative strategies when played against itself while being not exploitable by selfish players. We prove that in repeated symmetric games, this algorithm is a learning equilibrium. We illustrate the behavior of FCL on symmetric matrix and grid games, and its robustness to selfish learners.
Tasks
Published	2019-06-24
URL	https://arxiv.org/abs/1906.09831v2
PDF	https://arxiv.org/pdf/1906.09831v2.pdf
PWC	https://paperswithcode.com/paper/foolproof-cooperative-learning
Repo
Framework

Generative Memory for Lifelong Reinforcement Learning


Title	Generative Memory for Lifelong Reinforcement Learning
Authors	Aswin Raghavan, Jesse Hostetler, Sek Chai
Abstract	Our research is focused on understanding and applying biological memory transfers to new AI systems that can fundamentally improve their performance, throughout their fielded lifetime experience. We leverage current understanding of biological memory transfer to arrive at AI algorithms for memory consolidation and replay. In this paper, we propose the use of generative memory that can be recalled in batch samples to train a multi-task agent in a pseudo-rehearsal manner. We show results motivating the need for task-agnostic separation of latent space for the generative memory to address issues of catastrophic forgetting in lifelong learning.
Tasks
Published	2019-02-22
URL	http://arxiv.org/abs/1902.08349v1
PDF	http://arxiv.org/pdf/1902.08349v1.pdf
PWC	https://paperswithcode.com/paper/generative-memory-for-lifelong-reinforcement
Repo
Framework

Automated building image extraction from 360° panoramas for postdisaster evaluation


Title	Automated building image extraction from 360° panoramas for postdisaster evaluation
Authors	Ali Lenjani, Chul Min Yeum, Shirley Dyke, Ilias Bilionis
Abstract	After a disaster, teams of structural engineers collect vast amounts of images from damaged buildings to obtain new knowledge and extract lessons from the event. However, in many cases, the images collected are captured without sufficient spatial context. When damage is severe, it may be quite difficult to even recognize the building. Accessing images of the pre-disaster condition of those buildings is required to accurately identify the cause of the failure or the actual loss in the building. Here, to address this issue, we develop a method to automatically extract pre-event building images from 360o panorama images (panoramas). By providing a geotagged image collected near the target building as the input, panoramas close to the input image location are automatically downloaded through street view services (e.g., Google or Bing in the United States). By computing the geometric relationship between the panoramas and the target building, the most suitable projection direction for each panorama is identified to generate high-quality 2D images of the building. Region-based convolutional neural networks are exploited to recognize the building within those 2D images. Several panoramas are used so that the detected building images provide various viewpoints of the building. To demonstrate the capability of the technique, we consider residential buildings in Holiday Beach, Texas, the United States which experienced significant devastation in Hurricane Harvey in 2017. Using geotagged images gathered during actual post-disaster building reconnaissance missions, we verify the method by successfully extracting residential building images from Google Street View images, which were captured before the event.
Tasks
Published	2019-05-04
URL	https://arxiv.org/abs/1905.01524v2
PDF	https://arxiv.org/pdf/1905.01524v2.pdf
PWC	https://paperswithcode.com/paper/automated-building-image-extraction-from-360
Repo
Framework

Interactive Image Generation Using Scene Graphs


Title	Interactive Image Generation Using Scene Graphs
Authors	Gaurav Mittal, Shubham Agrawal, Anuva Agarwal, Sushant Mehta, Tanya Marwah
Abstract	Recent years have witnessed some exciting developments in the domain of generating images from scene-based text descriptions. These approaches have primarily focused on generating images from a static text description and are limited to generating images in a single pass. They are unable to generate an image interactively based on an incrementally additive text description (something that is more intuitive and similar to the way we describe an image). We propose a method to generate an image incrementally based on a sequence of graphs of scene descriptions (scene-graphs). We propose a recurrent network architecture that preserves the image content generated in previous steps and modifies the cumulative image as per the newly provided scene information. Our model utilizes Graph Convolutional Networks (GCN) to cater to variable-sized scene graphs along with Generative Adversarial image translation networks to generate realistic multi-object images without needing any intermediate supervision during training. We experiment with Coco-Stuff dataset which has multi-object images along with annotations describing the visual scene and show that our model significantly outperforms other approaches on the same dataset in generating visually consistent images for incrementally growing scene graphs.
Tasks	Image Generation
Published	2019-05-09
URL	https://arxiv.org/abs/1905.03743v1
PDF	https://arxiv.org/pdf/1905.03743v1.pdf
PWC	https://paperswithcode.com/paper/190503743
Repo
Framework

Simultaneous x, y Pixel Estimation and Feature Extraction for Multiple Small Objects in a Scene: A Description of the ALIEN Network


Title	Simultaneous x, y Pixel Estimation and Feature Extraction for Multiple Small Objects in a Scene: A Description of the ALIEN Network
Authors	Seth Zuckerman, Timothy Klein, Alexander Boxer, Christopher Goldman, Brian Lang
Abstract	We present a deep-learning network that detects multiple small objects (hundreds to thousands) in a scene while simultaneously estimating their x,y pixel locations together with a characteristic feature-set (for instance, target orientation and color). All estimations are performed in a single, forward pass which makes implementing the network fast and efficient. In this paper, we describe the architecture of our network — nicknamed ALIEN — and detail its performance when applied to vehicle detection.
Tasks
Published	2019-02-06
URL	http://arxiv.org/abs/1902.05387v1
PDF	http://arxiv.org/pdf/1902.05387v1.pdf
PWC	https://paperswithcode.com/paper/simultaneous-x-y-pixel-estimation-and-feature
Repo
Framework

Adaptive Context Network for Scene Parsing


Title	Adaptive Context Network for Scene Parsing
Authors	Jun Fu, Jing Liu, Yuhang Wang, Yong Li, Yongjun Bao, Jinhui Tang, Hanqing Lu
Abstract	Recent works attempt to improve scene parsing performance by exploring different levels of contexts, and typically train a well-designed convolutional network to exploit useful contexts across all pixels equally. However, in this paper, we find that the context demands are varying from different pixels or regions in each image. Based on this observation, we propose an Adaptive Context Network (ACNet) to capture the pixel-aware contexts by a competitive fusion of global context and local context according to different per-pixel demands. Specifically, when given a pixel, the global context demand is measured by the similarity between the global feature and its local feature, whose reverse value can be used to measure the local context demand. We model the two demand measurements by the proposed global context module and local context module, respectively, to generate adaptive contextual features. Furthermore, we import multiple such modules to build several adaptive context blocks in different levels of network to obtain a coarse-to-fine result. Finally, comprehensive experimental evaluations demonstrate the effectiveness of the proposed ACNet, and new state-of-the-arts performances are achieved on all four public datasets, i.e. Cityscapes, ADE20K, PASCAL Context, and COCO Stuff.
Tasks	Scene Parsing
Published	2019-11-05
URL	https://arxiv.org/abs/1911.01664v1
PDF	https://arxiv.org/pdf/1911.01664v1.pdf
PWC	https://paperswithcode.com/paper/adaptive-context-network-for-scene-parsing-1
Repo
Framework

Learning to Determine the Quality of News Headlines


Title	Learning to Determine the Quality of News Headlines
Authors	Amin Omidvar, Hossein Poormodheji, Aijun An, Gordon Edall
Abstract	Today, most newsreaders read the online version of news articles rather than traditional paper-based newspapers. Also, news media publishers rely heavily on the income generated from subscriptions and website visits made by newsreaders. Thus, online user engagement is a very important issue for online newspapers. Much effort has been spent on writing interesting headlines to catch the attention of online users. On the other hand, headlines should not be misleading (e.g., clickbaits); otherwise, readers would be disappointed when reading the content. In this paper, we propose four indicators to determine the quality of published news headlines based on their click count and dwell time, which are obtained by website log analysis. Then, we use soft target distribution of the calculated quality indicators to train our proposed deep learning model which can predict the quality of unpublished news headlines. The proposed model not only processes the latent features of both headline and body of the article to predict its headline quality but also considers the semantic relation between headline and body as well. To evaluate our model, we use a real dataset from a major Canadian newspaper. Results show our proposed model outperforms other state-of-the-art NLP models.
Tasks
Published	2019-11-26
URL	https://arxiv.org/abs/1911.11139v1
PDF	https://arxiv.org/pdf/1911.11139v1.pdf
PWC	https://paperswithcode.com/paper/learning-to-determine-the-quality-of-news
Repo
Framework

PDA: Progressive Data Augmentation for General Robustness of Deep Neural Networks


Title	PDA: Progressive Data Augmentation for General Robustness of Deep Neural Networks
Authors	Hang Yu, Aishan Liu, Xianglong Liu, Gengchao Li, Ping Luo, Ran Cheng, Jichen Yang, Chongzhi Zhang
Abstract	Adversarial images are designed to mislead deep neural networks (DNNs), attracting great attention in recent years. Although several defense strategies achieved encouraging robustness against adversarial samples, most of them fail to improve the robustness on common corruptions such as noise, blur, and weather/digital effects (e.g. frost, pixelate). To address this problem, we propose a simple yet effective method, named Progressive Data Augmentation (PDA), which enables general robustness of DNNs by progressively injecting diverse adversarial noises during training. In other words, DNNs trained with PDA are able to obtain more robustness against both adversarial attacks as well as common corruptions than the recent state-of-the-art methods. We also find that PDA is more efficient than prior arts and able to prevent accuracy drop on clean samples without being attacked. Furthermore, we theoretically show that PDA can control the perturbation bound and guarantee better generalization ability than existing work. Extensive experiments on many benchmarks such as CIFAR-10, SVHN, and ImageNet demonstrate that PDA significantly outperforms its counterparts in various experimental setups.
Tasks	Data Augmentation
Published	2019-09-11
URL	https://arxiv.org/abs/1909.04839v3
PDF	https://arxiv.org/pdf/1909.04839v3.pdf
PWC	https://paperswithcode.com/paper/towards-noise-robust-neural-networks-via
Repo
Framework