January 27, 2020

3079 words 15 mins read

Paper Group ANR 1238

Using natural language processing techniques to extract information on the properties and functionalities of energetic materials from large text corpora. Incremental learning of environment interactive structures from trajectories of individuals. Closed-Form Optimal Two-View Triangulation Based on Angular Errors. Using Subset Log-Likelihoods to Tri …

Using natural language processing techniques to extract information on the properties and functionalities of energetic materials from large text corpora


Title	Using natural language processing techniques to extract information on the properties and functionalities of energetic materials from large text corpora
Authors	Daniel C. Elton, Dhruv Turakhia, Nischal Reddy, Zois Boukouvalas, Mark D. Fuge, Ruth M. Doherty, Peter W. Chung
Abstract	The number of scientific journal articles and reports being published about energetic materials every year is growing exponentially, and therefore extracting relevant information and actionable insights from the latest research is becoming a considerable challenge. In this work we explore how techniques from natural language processing and machine learning can be used to automatically extract chemical insights from large collections of documents. We first describe how to download and process documents from a variety of sources - journal articles, conference proceedings (including NTREM), the US Patent & Trademark Office, and the Defense Technical Information Center archive on archive.org. We present a custom NLP pipeline which uses open source NLP tools to identify the names of chemical compounds and relates them to function words (“underwater”, “rocket”, “pyrotechnic”) and property words (“elastomer”, “non-toxic”). After explaining how word embeddings work we compare the utility of two popular word embeddings - word2vec and GloVe. Chemical-chemical and chemical-application relationships are obtained by doing computations with word vectors. We show that word embeddings capture latent information about energetic materials, so that related materials appear close together in the word embedding space.
Tasks	Word Embeddings
Published	2019-03-01
URL	http://arxiv.org/abs/1903.00415v1
PDF	http://arxiv.org/pdf/1903.00415v1.pdf
PWC	https://paperswithcode.com/paper/using-natural-language-processing-techniques
Repo
Framework

Incremental learning of environment interactive structures from trajectories of individuals


Title	Incremental learning of environment interactive structures from trajectories of individuals
Authors	Damian Campo, Vahid Bastani, Lucio Marcenaro, Carlo Regazzoni
Abstract	This work proposes a novel method for estimating the influence that unknown static objects might have over mobile agents. Since the motion of agents can be affected by the presence of fixed objects, it is possible use the information about trajectories deviations to infer the presence of obstacles and estimate the forces involved in a scene. Artificial neural networks are used to estimate a non-parametric function related to the velocity field influencing moving agents. The proposed method is able to incrementally learn the velocity fields due to external static objects within the monitored environment. It determines whether an object has a repulsive or an attractive influence and provides an estimation of its position and size. As stationarity is assumed, i.e., time-invariance of force fields, learned observation models can be used as prior knowledge for estimating hierarchically the properties of new objects in a scene.
Tasks
Published	2019-09-09
URL	https://arxiv.org/abs/1909.03980v1
PDF	https://arxiv.org/pdf/1909.03980v1.pdf
PWC	https://paperswithcode.com/paper/incremental-learning-of-environment
Repo
Framework

Closed-Form Optimal Two-View Triangulation Based on Angular Errors


Title	Closed-Form Optimal Two-View Triangulation Based on Angular Errors
Authors	Seong Hun Lee, Javier Civera
Abstract	In this paper, we study closed-form optimal solutions to two-view triangulation with known internal calibration and pose. By formulating the triangulation problem as $L_1$ and $L_\infty$ minimization of angular reprojection errors, we derive the exact closed-form solutions that guarantee global optimality under respective cost functions. To the best of our knowledge, we are the first to present such solutions. Since the angular error is rotationally invariant, our solutions can be applied for any type of central cameras, be it perspective, fisheye or omnidirectional. Our methods also require significantly less computation than the existing optimal methods. Experimental results on synthetic and real datasets validate our theoretical derivations.
Tasks	Calibration
Published	2019-03-21
URL	https://arxiv.org/abs/1903.09115v3
PDF	https://arxiv.org/pdf/1903.09115v3.pdf
PWC	https://paperswithcode.com/paper/closed-form-optimal-triangulation-based-on
Repo
Framework

Using Subset Log-Likelihoods to Trim Outliers in Gaussian Mixture Models


Title	Using Subset Log-Likelihoods to Trim Outliers in Gaussian Mixture Models
Authors	Katharine M. Clark, Paul D. McNicholas
Abstract	Mixtures of Gaussian distributions are a popular choice in model-based clustering. Outliers can affect parameters estimation and, as such, must be accounted for. Predicting the proportion of outliers correctly is paramount as it minimizes misclassification error. It is proved that, for a finite Gaussian mixture model, the log-likelihoods of the subset models are distributed according to a mixture of beta distributions. An algorithm is then proposed that predicts the proportion of outliers by measuring the adherence of a set of subset log-likelihoods to a beta mixture reference distribution. This algorithm removes the least likely points, which are deemed outliers, until model assumptions are met.
Tasks
Published	2019-07-02
URL	https://arxiv.org/abs/1907.01136v3
PDF	https://arxiv.org/pdf/1907.01136v3.pdf
PWC	https://paperswithcode.com/paper/using-subset-log-likelihoods-to-trim-outliers
Repo
Framework

WiderPerson: A Diverse Dataset for Dense Pedestrian Detection in the Wild


Title	WiderPerson: A Diverse Dataset for Dense Pedestrian Detection in the Wild
Authors	Shifeng Zhang, Yiliang Xie, Jun Wan, Hansheng Xia, Stan Z. Li, Guodong Guo
Abstract	Pedestrian detection has achieved significant progress with the availability of existing benchmark datasets. However, there is a gap in the diversity and density between real world requirements and current pedestrian detection benchmarks: 1) most of existing datasets are taken from a vehicle driving through the regular traffic scenario, usually leading to insufficient diversity; 2) crowd scenarios with highly occluded pedestrians are still under represented, resulting in low density. To narrow this gap and facilitate future pedestrian detection research, we introduce a large and diverse dataset named WiderPerson for dense pedestrian detection in the wild. This dataset involves five types of annotations in a wide range of scenarios, no longer limited to the traffic scenario. There are a total of $13,382$ images with $399,786$ annotations, i.e., $29.87$ annotations per image, which means this dataset contains dense pedestrians with various kinds of occlusions. Hence, pedestrians in the proposed dataset are extremely challenging due to large variations in the scenario and occlusion, which is suitable to evaluate pedestrian detectors in the wild. We introduce an improved Faster R-CNN and the vanilla RetinaNet to serve as baselines for the new pedestrian detection benchmark. Several experiments are conducted on previous datasets including Caltech-USA and CityPersons to analyze the generalization capabilities of the proposed dataset and we achieve state-of-the-art performances on these previous datasets without bells and whistles. Finally, we analyze common failure cases and find the classification ability of pedestrian detector needs to be improved to reduce false alarm and miss detection rates. The proposed dataset is available at http://www.cbsr.ia.ac.cn/users/sfzhang/WiderPerson
Tasks	Pedestrian Detection
Published	2019-09-25
URL	https://arxiv.org/abs/1909.12118v1
PDF	https://arxiv.org/pdf/1909.12118v1.pdf
PWC	https://paperswithcode.com/paper/widerperson-a-diverse-dataset-for-dense
Repo
Framework

Location reference identification from tweets during emergencies: A deep learning approach


Title	Location reference identification from tweets during emergencies: A deep learning approach
Authors	Abhinav Kumar, Jyoti Prakash Singh
Abstract	Twitter is recently being used during crises to communicate with officials and provide rescue and relief operation in real time. The geographical location information of the event, as well as users, are vitally important in such scenarios. The identification of geographic location is one of the challenging tasks as the location information fields, such as user location and place name of tweets are not reliable. The extraction of location information from tweet text is difficult as it contains a lot of non-standard English, grammatical errors, spelling mistakes, non-standard abbreviations, and so on. This research aims to extract location words used in the tweet using a Convolutional Neural Network (CNN) based model. We achieved the exact matching score of 0.929, Hamming loss of 0.002, and $F_1$-score of 0.96 for the tweets related to the earthquake. Our model was able to extract even three- to four-word long location references which is also evident from the exact matching score of over 92%. The findings of this paper can help in early event localization, emergency situations, real-time road traffic management, localized advertisement, and in various location-based services.
Tasks
Published	2019-01-24
URL	http://arxiv.org/abs/1901.08241v1
PDF	http://arxiv.org/pdf/1901.08241v1.pdf
PWC	https://paperswithcode.com/paper/location-reference-identification-from-tweets
Repo
Framework

Improving Strong-Scaling of CNN Training by Exploiting Finer-Grained Parallelism


Title	Improving Strong-Scaling of CNN Training by Exploiting Finer-Grained Parallelism
Authors	Nikoli Dryden, Naoya Maruyama, Tom Benson, Tim Moon, Marc Snir, Brian Van Essen
Abstract	Scaling CNN training is necessary to keep up with growing datasets and reduce training time. We also see an emerging need to handle datasets with very large samples, where memory requirements for training are large. Existing training frameworks use a data-parallel approach that partitions samples within a mini-batch, but limits to scaling the mini-batch size and memory consumption makes this untenable for large samples. We describe and implement new approaches to convolution, which parallelize using spatial decomposition or a combination of sample and spatial decomposition. This introduces many performance knobs for a network, so we develop a performance model for CNNs and present a method for using it to automatically determine efficient parallelization strategies. We evaluate our algorithms with microbenchmarks and image classification with ResNet-50. Our algorithms allow us to prototype a model for a mesh-tangling dataset, where sample sizes are very large. We show that our parallelization achieves excellent strong and weak scaling and enables training for previously unreachable datasets.
Tasks	Image Classification
Published	2019-03-15
URL	http://arxiv.org/abs/1903.06681v1
PDF	http://arxiv.org/pdf/1903.06681v1.pdf
PWC	https://paperswithcode.com/paper/improving-strong-scaling-of-cnn-training-by
Repo
Framework

A Review-Driven Neural Model for Sequential Recommendation


Title	A Review-Driven Neural Model for Sequential Recommendation
Authors	Chenliang Li, Xichuan Niu, Xiangyang Luo, Zhenzhong Chen, Cong Quan
Abstract	Writing review for a purchased item is a unique channel to express a user’s opinion in E-Commerce. Recently, many deep learning based solutions have been proposed by exploiting user reviews for rating prediction. In contrast, there has been few attempt to enlist the semantic signals covered by user reviews for the task of collaborative filtering. In this paper, we propose a novel review-driven neural sequential recommendation model (named RNS) by considering users’ intrinsic preference (long-term) and sequential patterns (short-term). In detail, RNS is devised to encode each user or item with the aspect-aware representations extracted from the reviews. Given a sequence of historical purchased items for a user, we devise a novel hierarchical attention over attention mechanism to capture sequential patterns at both union-level and individual-level. Extensive experiments on three real-world datasets of different domains demonstrate that RNS obtains significant performance improvement over uptodate state-of-the-art sequential recommendation models.
Tasks
Published	2019-07-01
URL	https://arxiv.org/abs/1907.00590v1
PDF	https://arxiv.org/pdf/1907.00590v1.pdf
PWC	https://paperswithcode.com/paper/a-review-driven-neural-model-for-sequential
Repo
Framework

Towards User Empowerment


Title	Towards User Empowerment
Authors	Martin Pawelczyk, Johannes Haug, Klaus Broelemann, Gjergji Kasneci
Abstract	Counterfactual explanations can be obtained by identifying the smallest change made to a feature vector to qualitatively influence a prediction; for example, from ‘loan rejected’ to ‘awarded’ or from ‘high risk of cardiovascular disease’ to ‘low risk’. Previous approaches often emphasized that counterfactuals should be easily interpretable to humans, motivating sparse solutions with few changes to the feature vectors. However, these approaches would not ensure that the produced counterfactuals be proximate (i.e., not local outliers) and connected to regions with substantial data density (i.e., close to correctly classified observations), two requirements known as counterfactual faithfulness. These requirements are fundamental when making suggestions to individuals that are indeed attainable. Our contribution is twofold. On one hand, we suggest to complement the catalogue of counterfactual quality measures [1] using a criterion to quantify the degree of difficulty for a certain counterfactual suggestion. On the other hand, drawing ideas from the manifold learning literature, we develop a framework that generates attainable counterfactuals. We suggest the counterfactual conditional heterogeneous variational autoencoder (C-CHVAE) to identify attainable counterfactuals that lie within regions of high data density.
Tasks
Published	2019-10-21
URL	https://arxiv.org/abs/1910.09398v1
PDF	https://arxiv.org/pdf/1910.09398v1.pdf
PWC	https://paperswithcode.com/paper/towards-user-empowerment
Repo
Framework

What Should I Do Now? Marrying Reinforcement Learning and Symbolic Planning


Title	What Should I Do Now? Marrying Reinforcement Learning and Symbolic Planning
Authors	Daniel Gordon, Dieter Fox, Ali Farhadi
Abstract	Long-term planning poses a major difficulty to many reinforcement learning algorithms. This problem becomes even more pronounced in dynamic visual environments. In this work we propose Hierarchical Planning and Reinforcement Learning (HIP-RL), a method for merging the benefits and capabilities of Symbolic Planning with the learning abilities of Deep Reinforcement Learning. We apply HIPRL to the complex visual tasks of interactive question answering and visual semantic planning and achieve state-of-the-art results on three challenging datasets all while taking fewer steps at test time and training in fewer iterations. Sample results can be found at youtu.be/0TtWJ_0mPfI
Tasks	Question Answering
Published	2019-01-06
URL	http://arxiv.org/abs/1901.01492v1
PDF	http://arxiv.org/pdf/1901.01492v1.pdf
PWC	https://paperswithcode.com/paper/what-should-i-do-now-marrying-reinforcement
Repo
Framework

Do Explanations Reflect Decisions? A Machine-centric Strategy to Quantify the Performance of Explainability Algorithms


Title	Do Explanations Reflect Decisions? A Machine-centric Strategy to Quantify the Performance of Explainability Algorithms
Authors	Zhong Qiu Lin, Mohammad Javad Shafiee, Stanislav Bochkarev, Michael St. Jules, Xiao Yu Wang, Alexander Wong
Abstract	There has been a significant surge of interest recently around the concept of explainable artificial intelligence (XAI), where the goal is to produce an interpretation for a decision made by a machine learning algorithm. Of particular interest is the interpretation of how deep neural networks make decisions, given the complexity and `black box’ nature of such networks. Given the infancy of the field, there has been very limited exploration into the assessment of the performance of explainability methods, with most evaluations centered around subjective visual interpretation of the produced interpretations. In this study, we explore a more machine-centric strategy for quantifying the performance of explainability methods on deep neural networks via the notion of decision-making impact analysis. We introduce two quantitative performance metrics: i) Impact Score, which assesses the percentage of critical factors with either strong confidence reduction impact or decision changing impact, and ii) Impact Coverage, which assesses the percentage coverage of adversarially impacted factors in the input. A comprehensive analysis using this approach was conducted on several state-of-the-art explainability methods (LIME, SHAP, Expected Gradients, GSInquire) on a ResNet-50 deep convolutional neural network using a subset of ImageNet for the task of image classification. Experimental results show that the critical regions identified by LIME within the tested images had the lowest impact on the decision-making process of the network (~38%), with progressive increase in decision-making impact for SHAP (~44%), Expected Gradients (~51%), and GSInquire (~76%). While by no means perfect, the hope is that the proposed machine-centric strategy helps push the conversation forward towards better metrics for evaluating explainability methods and improve trust in deep neural networks. \|
Tasks	Decision Making, Image Classification
Published	2019-10-16
URL	https://arxiv.org/abs/1910.07387v2
PDF	https://arxiv.org/pdf/1910.07387v2.pdf
PWC	https://paperswithcode.com/paper/explaining-with-impact-a-machine-centric
Repo
Framework

Learning to Blindly Assess Image Quality in the Laboratory and Wild


Title	Learning to Blindly Assess Image Quality in the Laboratory and Wild
Authors	Weixia Zhang, Kede Ma, Guangtao Zhai, Xiaokang Yang
Abstract	Computational models for blind image quality assessment (BIQA) are typically trained in well-controlled laboratory environments with limited generalizability to realistically distorted images. Similarly, BIQA models optimized for images captured in the wild cannot adequately handle synthetically distorted images. To face the cross-distortion-scenario challenge, we develop a BIQA model and an approach of training it on multiple IQA databases (of different distortion scenarios) simultaneously. A key step in our approach is to create and combine image pairs within individual databases as the training set, which effectively bypasses the issue of perceptual scale realignment. We compute a continuous quality annotation for each pair from the corresponding human opinions, indicating the probability of one image having better perceptual quality. We train a deep neural network for BIQA over the training set of massive image pairs by minimizing the fidelity loss. Experiments on six IQA databases demonstrate that the optimized model by the proposed training strategy is effective in blindly assessing image quality in the laboratory and wild, outperforming previous BIQA methods by a large margin.
Tasks	Blind Image Quality Assessment, Image Quality Assessment, Learning-To-Rank
Published	2019-07-01
URL	https://arxiv.org/abs/1907.00516v2
PDF	https://arxiv.org/pdf/1907.00516v2.pdf
PWC	https://paperswithcode.com/paper/learning-to-blindly-assess-image-quality-in
Repo
Framework

Learning step sizes for unfolded sparse coding


Title	Learning step sizes for unfolded sparse coding
Authors	Pierre Ablin, Thomas Moreau, Mathurin Massias, Alexandre Gramfort
Abstract	Sparse coding is typically solved by iterative optimization techniques, such as the Iterative Shrinkage-Thresholding Algorithm (ISTA). Unfolding and learning weights of ISTA using neural networks is a practical way to accelerate estimation. In this paper, we study the selection of adapted step sizes for ISTA. We show that a simple step size strategy can improve the convergence rate of ISTA by leveraging the sparsity of the iterates. However, it is impractical in most large-scale applications. Therefore, we propose a network architecture where only the step sizes of ISTA are learned. We demonstrate that for a large class of unfolded algorithms, if the algorithm converges to the solution of the Lasso, its last layers correspond to ISTA with learned step sizes. Experiments show that our method is competitive with state-of-the-art networks when the solutions are sparse enough.
Tasks
Published	2019-05-27
URL	https://arxiv.org/abs/1905.11071v1
PDF	https://arxiv.org/pdf/1905.11071v1.pdf
PWC	https://paperswithcode.com/paper/learning-step-sizes-for-unfolded-sparse
Repo
Framework

S&CNet: Monocular Depth Completion for Autonomous Systems and 3D Reconstruction


Title	S&CNet: Monocular Depth Completion for Autonomous Systems and 3D Reconstruction
Authors	Lei Zhang, Weihai Chen, Chao Hu, Xingming Wu, Zhengguo Li
Abstract	Dense depth completion is essential for autonomous systems and 3D reconstruction. In this paper, a lightweight yet efficient network (S&CNet) is proposed to obtain a good trade-off between efficiency and accuracy for the dense depth completion. A dual-stream attention module (S&C enhancer) is introduced to measure both spatial-wise and the channel-wise global-range relationship of extracted features so as to improve the performance. A coarse-to-fine network is designed and the proposed S&C enhancer is plugged into the coarse estimation network between its encoder and decoder network. Experimental results demonstrate that our approach achieves competitive performance with existing works on KITTI dataset but almost four times faster. The proposed S&C enhancer can be plugged into other existing works and boost their performance significantly with a negligible additional computational cost.
Tasks	3D Reconstruction, Autonomous Driving, Depth Completion
Published	2019-07-13
URL	https://arxiv.org/abs/1907.06071v2
PDF	https://arxiv.org/pdf/1907.06071v2.pdf
PWC	https://paperswithcode.com/paper/scnet-a-enhanced-coarse-to-fine-framework-for
Repo
Framework

A Case Study: Exploiting Neural Machine Translation to Translate CUDA to OpenCL


Title	A Case Study: Exploiting Neural Machine Translation to Translate CUDA to OpenCL
Authors	Yonghae Kim, Hyesoon Kim
Abstract	The sequence-to-sequence (seq2seq) model for neural machine translation has significantly improved the accuracy of language translation. There have been new efforts to use this seq2seq model for program language translation or program comparisons. In this work, we present the detailed steps of using a seq2seq model to translate CUDA programs to OpenCL programs, which both have very similar programming styles. Our work shows (i) a training input set generation method, (ii) pre/post processing, and (iii) a case study using Polybench-gpu-1.0, NVIDIA SDK, and Rodinia benchmarks.
Tasks	Machine Translation
Published	2019-05-18
URL	https://arxiv.org/abs/1905.07653v1
PDF	https://arxiv.org/pdf/1905.07653v1.pdf
PWC	https://paperswithcode.com/paper/a-case-study-exploiting-neural-machine
Repo
Framework