January 26, 2020

3291 words 16 mins read

Paper Group ANR 1504

Improving Multi-turn Dialogue Modelling with Utterance ReWriter. Analysis of the hands in egocentric vision: A survey. A Ride-Matching Strategy For Large Scale Dynamic Ridesharing Services Based on Polar Coordinates. Naive Gabor Networks for Hyperspectral Image Classification. On Functional Test Generation for Deep Neural Network IPs. Interpretable …

Improving Multi-turn Dialogue Modelling with Utterance ReWriter


Title	Improving Multi-turn Dialogue Modelling with Utterance ReWriter
Authors	Hui Su, Xiaoyu Shen, Rongzhi Zhang, Fei Sun, Pengwei Hu, Cheng Niu, Jie Zhou
Abstract	Recent research has made impressive progress in single-turn dialogue modelling. In the multi-turn setting, however, current models are still far from satisfactory. One major challenge is the frequently occurred coreference and information omission in our daily conversation, making it hard for machines to understand the real intention. In this paper, we propose rewriting the human utterance as a pre-process to help multi-turn dialgoue modelling. Each utterance is first rewritten to recover all coreferred and omitted information. The next processing steps are then performed based on the rewritten utterance. To properly train the utterance rewriter, we collect a new dataset with human annotations and introduce a Transformer-based utterance rewriting architecture using the pointer network. We show the proposed architecture achieves remarkably good performance on the utterance rewriting task. The trained utterance rewriter can be easily integrated into online chatbots and brings general improvement over different domains.
Tasks
Published	2019-06-14
URL	https://arxiv.org/abs/1906.07004v1
PDF	https://arxiv.org/pdf/1906.07004v1.pdf
PWC	https://paperswithcode.com/paper/improving-multi-turn-dialogue-modelling-with
Repo
Framework

Analysis of the hands in egocentric vision: A survey


Title	Analysis of the hands in egocentric vision: A survey
Authors	Andrea Bandini, José Zariffa
Abstract	Egocentric vision (a.k.a. first-person vision - FPV) applications have thrived over the past few years, thanks to the availability of affordable wearable cameras and large annotated datasets. The position of the wearable camera (usually mounted on the head) allows recording exactly what the camera wearers have in front of them, in particular hands and manipulated objects. This intrinsic advantage enables the study of the hands from multiple perspectives: localizing hands and their parts within the images; understanding what actions and activities the hands are involved in; and developing human-computer interfaces that rely on hand gestures. In this survey, we review the literature that focuses on the hands using egocentric vision, categorizing the existing approaches into: localization (where are the hands or parts of them?); interpretation (what are the hands doing?); and application (e.g., systems that used egocentric hand cues for solving a specific problem). Moreover, a list of the most prominent datasets with hand-based annotations is provided.
Tasks
Published	2019-12-23
URL	https://arxiv.org/abs/1912.10867v2
PDF	https://arxiv.org/pdf/1912.10867v2.pdf
PWC	https://paperswithcode.com/paper/analysis-of-the-hands-in-egocentric-vision-a
Repo
Framework

A Ride-Matching Strategy For Large Scale Dynamic Ridesharing Services Based on Polar Coordinates


Title	A Ride-Matching Strategy For Large Scale Dynamic Ridesharing Services Based on Polar Coordinates
Authors	Jiyao Li, Vicki H. Allan
Abstract	In this paper, we study a challenging problem of how to pool multiple ride-share trip requests in real time under an uncertain environment. The goals are better performance metrics of efficiency and acceptable satisfaction of riders. To solve the problem effectively, an objective function that compromises the benefits and losses of dynamic ridesharing service is proposed. The Polar Coordinates based Ride-Matching strategy (PCRM) that can adapt to the satisfaction of riders on board is also addressed. In the experiment, large scale data sets from New York City (NYC) are applied. We do a case study to identify the best set of parameters of the dynamic ridesharing service with a training set of 135,252 trip requests. In addition, we also use a testing set containing 427,799 trip requests and two state-of-the-art approaches as baselines to estimate the effectiveness of our method. The experimental results show that on average 38% of traveling distance can be saved, nearly 100% of passengers can be served and each rider only spends an additional 3.8 minutes in ridesharing trips compared to single rider service.
Tasks
Published	2019-06-08
URL	https://arxiv.org/abs/1906.03394v1
PDF	https://arxiv.org/pdf/1906.03394v1.pdf
PWC	https://paperswithcode.com/paper/a-ride-matching-strategy-for-large-scale
Repo
Framework

Naive Gabor Networks for Hyperspectral Image Classification


Title	Naive Gabor Networks for Hyperspectral Image Classification
Authors	Chenying Liu, Jun Li, Lin He, Antonio J. Plaza, Shutao Li, Bo Li
Abstract	Recently, many convolutional neural network (CNN) methods have been designed for hyperspectral image (HSI) classification since CNNs are able to produce good representations of data, which greatly benefits from a huge number of parameters. However, solving such a high-dimensional optimization problem often requires a large amount of training samples in order to avoid overfitting. Additionally, it is a typical non-convex problem affected by many local minima and flat regions. To address these problems, in this paper, we introduce naive Gabor Networks or Gabor-Nets which, for the first time in the literature, design and learn CNN kernels strictly in the form of Gabor filters, aiming to reduce the number of involved parameters and constrain the solution space, and hence improve the performances of CNNs. Specifically, we develop an innovative phase-induced Gabor kernel, which is trickily designed to perform the Gabor feature learning via a linear combination of local low-frequency and high-frequency components of data controlled by the kernel phase. With the phase-induced Gabor kernel, the proposed Gabor-Nets gains the ability to automatically adapt to the local harmonic characteristics of the HSI data and thus yields more representative harmonic features. Also, this kernel can fulfill the traditional complex-valued Gabor filtering in a real-valued manner, hence making Gabor-Nets easily perform in a usual CNN thread. We evaluated our newly developed Gabor-Nets on three well-known HSIs, suggesting that our proposed Gabor-Nets can significantly improve the performance of CNNs, particularly with a small training set.
Tasks	Hyperspectral Image Classification, Image Classification
Published	2019-12-09
URL	https://arxiv.org/abs/1912.03991v2
PDF	https://arxiv.org/pdf/1912.03991v2.pdf
PWC	https://paperswithcode.com/paper/naive-gabor-networks
Repo
Framework

On Functional Test Generation for Deep Neural Network IPs


Title	On Functional Test Generation for Deep Neural Network IPs
Authors	Bo Luo, Yu Li, Lingxiao Wei, Qiang Xu
Abstract	Machine learning systems based on deep neural networks (DNNs) produce state-of-the-art results in many applications. Considering the large amount of training data and know-how required to generate the network, it is more practical to use third-party DNN intellectual property (IP) cores for many designs. No doubt to say, it is essential for DNN IP vendors to provide test cases for functional validation without leaking their parameters to IP users. To satisfy this requirement, we propose to effectively generate test cases that activate parameters as many as possible and propagate their perturbations to outputs. Then the functionality of DNN IPs can be validated by only checking their outputs. However, it is difficult considering large numbers of parameters and highly non-linearity of DNNs. In this paper, we tackle this problem by judiciously selecting samples from the DNN training set and applying a gradient-based method to generate new test cases. Experimental results demonstrate the efficacy of our proposed solution.
Tasks
Published	2019-11-23
URL	https://arxiv.org/abs/1911.11550v1
PDF	https://arxiv.org/pdf/1911.11550v1.pdf
PWC	https://paperswithcode.com/paper/on-functional-test-generation-for-deep-neural
Repo
Framework

Interpretable Subgroup Discovery in Treatment Effect Estimation with Application to Opioid Prescribing Guidelines


Title	Interpretable Subgroup Discovery in Treatment Effect Estimation with Application to Opioid Prescribing Guidelines
Authors	Chirag Nagpal, Dennis Wei, Bhanukiran Vinzamuri, Monica Shekhar, Sara E. Berger, Subhro Das, Kush R. Varshney
Abstract	The dearth of prescribing guidelines for physicians is one key driver of the current opioid epidemic in the United States. In this work, we analyze medical and pharmaceutical claims data to draw insights on characteristics of patients who are more prone to adverse outcomes after an initial synthetic opioid prescription. Toward this end, we propose a generative model that allows discovery from observational data of subgroups that demonstrate an enhanced or diminished causal effect due to treatment. Our approach models these sub-populations as a mixture distribution, using sparsity to enhance interpretability, while jointly learning nonlinear predictors of the potential outcomes to better adjust for confounding. The approach leads to human-interpretable insights on discovered subgroups, improving the practical utility for decision support
Tasks
Published	2019-05-08
URL	https://arxiv.org/abs/1905.03297v3
PDF	https://arxiv.org/pdf/1905.03297v3.pdf
PWC	https://paperswithcode.com/paper/190503297
Repo
Framework

DADA-2000: Can Driving Accident be Predicted by Driver Attention? Analyzed by A Benchmark


Title	DADA-2000: Can Driving Accident be Predicted by Driver Attention? Analyzed by A Benchmark
Authors	Jianwu Fang, Dingxin Yan, Jiahuan Qiao, Jianru Xue, He Wang, Sen Li
Abstract	Driver attention prediction is currently becoming the focus in safe driving research community, such as the DR(eye)VE project and newly emerged Berkeley DeepDrive Attention (BDD-A) database in critical situations. In safe driving, an essential task is to predict the incoming accidents as early as possible. BDD-A was aware of this problem and collected the driver attention in laboratory because of the rarity of such scenes. Nevertheless, BDD-A focuses the critical situations which do not encounter actual accidents, and just faces the driver attention prediction task, without a close step for accident prediction. In contrast to this, we explore the view of drivers’ eyes for capturing multiple kinds of accidents, and construct a more diverse and larger video benchmark than ever before with the driver attention and the driving accident annotation simultaneously (named as DADA-2000), which has 2000 video clips owning about 658,476 frames on 54 kinds of accidents. These clips are crowd-sourced and captured in various occasions (highway, urban, rural, and tunnel), weather (sunny, rainy and snowy) and light conditions (daytime and nighttime). For the driver attention representation, we collect the maps of fixations, saccade scan path and focusing time. The accidents are annotated by their categories, the accident window in clips and spatial locations of the crash-objects. Based on the analysis, we obtain a quantitative and positive answer for the question in this paper.
Tasks	Driver Attention Monitoring
Published	2019-04-23
URL	http://arxiv.org/abs/1904.12634v1
PDF	http://arxiv.org/pdf/1904.12634v1.pdf
PWC	https://paperswithcode.com/paper/190412634
Repo
Framework

Preventing the Generation of Inconsistent Sets of Classification Rules


Title	Preventing the Generation of Inconsistent Sets of Classification Rules
Authors	Thiago Zafalon Miranda, Diorge Brognara Sardinha, Ricardo Cerri
Abstract	In recent years, the interest in interpretable classification models has grown. One of the proposed ways to improve the interpretability of a rule-based classification model is to use sets (unordered collections) of rules, instead of lists (ordered collections) of rules. One of the problems associated with sets is that multiple rules may cover a single instance, but predict different classes for it, thus requiring a conflict resolution strategy. In this work, we propose two algorithms capable of finding feature-space regions inside which any created rule would be consistent with the already existing rules, preventing inconsistencies from arising. Our algorithms do not generate classification models, but are instead meant to enhance algorithms that do so, such as Learning Classifier Systems. Both algorithms are described and analyzed exclusively from a theoretical perspective, since we have not modified a model-generating algorithm to incorporate our proposed solutions yet. This work presents the novelty of using conflict avoidance strategies instead of conflict resolution strategies.
Tasks
Published	2019-08-23
URL	https://arxiv.org/abs/1908.09652v2
PDF	https://arxiv.org/pdf/1908.09652v2.pdf
PWC	https://paperswithcode.com/paper/preventing-the-generation-of-inconsistent
Repo
Framework

Flattening a Hierarchical Clustering through Active Learning


Title	Flattening a Hierarchical Clustering through Active Learning
Authors	Fabio Vitale, Anand Rajagopalan, Claudio Gentile
Abstract	We investigate active learning by pairwise similarity over the leaves of trees originating from hierarchical clustering procedures. In the realizable setting, we provide a full characterization of the number of queries needed to achieve perfect reconstruction of the tree cut. In the non-realizable setting, we rely on known important-sampling procedures to obtain regret and query complexity bounds. Our algorithms come with theoretical guarantees on the statistical error and, more importantly, lend themselves to linear-time implementations in the relevant parameters of the problem. We discuss such implementations, prove running time guarantees for them, and present preliminary experiments on real-world datasets showing the compelling practical performance of our algorithms as compared to both passive learning and simple active learning baselines.
Tasks	Active Learning
Published	2019-06-22
URL	https://arxiv.org/abs/1906.09458v2
PDF	https://arxiv.org/pdf/1906.09458v2.pdf
PWC	https://paperswithcode.com/paper/flattening-a-hierarchical-clustering-through
Repo
Framework

Learning beyond Predefined Label Space via Bayesian Nonparametric Topic Modelling


Title	Learning beyond Predefined Label Space via Bayesian Nonparametric Topic Modelling
Authors	Changying Du, Fuzhen Zhuang, Jia He, Qing He, Guoping Long
Abstract	In real world machine learning applications, testing data may contain some meaningful new categories that have not been seen in labeled training data. To simultaneously recognize new data categories and assign most appropriate category labels to the data actually from known categories, existing models assume the number of unknown new categories is pre-specified, though it is difficult to determine in advance. In this paper, we propose a Bayesian nonparametric topic model to automatically infer this number, based on the hierarchical Dirichlet process and the notion of latent Dirichlet allocation. Exact inference in our model is intractable, so we provide an efficient collapsed Gibbs sampling algorithm for approximate posterior inference. Extensive experiments on various text data sets show that: (a) compared with parametric approaches that use pre-specified true number of new categories, the proposed nonparametric approach can yield comparable performance; and (b) when the exact number of new categories is unavailable, i.e. the parametric approaches only have a rough idea about the new categories, our approach has evident performance advantages.
Tasks
Published	2019-10-10
URL	https://arxiv.org/abs/1910.04420v1
PDF	https://arxiv.org/pdf/1910.04420v1.pdf
PWC	https://paperswithcode.com/paper/learning-beyond-predefined-label-space-via
Repo
Framework

Eelgrass beds and oyster farming at a lagoon before and after the Great East Japan Earthquake 2011: potential to apply deep learning at a coastal area


Title	Eelgrass beds and oyster farming at a lagoon before and after the Great East Japan Earthquake 2011: potential to apply deep learning at a coastal area
Authors	Takehisa Yamakita
Abstract	There is a small number of case studies of automatic land cover classification on the coastal area. Here, I test extraction of seagrass beds, sandy area, oyster farming rafts at Mangoku-ura Lagoon, Miyagi, Japan by comparing manual tracing, simple image segmentation, and image transformation using deep learning. The result was used to extract the changes before and after the earthquake and tsunami. The output resolution was best in the image transformation method, which showed more than 69% accuracy for vegetation classification by an assessment using random points on independent test data. The distribution of oyster farming rafts was detected by the segmentation model. Assessment of the change before and after the earthquake by the manual tracing and image transformation result revealed increase of sand area and decrease of the vegetation. By the segmentation model only the decrease of the oyster farming was detected. These results demonstrate the potential to extract the spatial pattern of these elements after an earthquake and tsunami. Index Terms: Great East Japan Earthquake of 2011, Land use land cover (LULC), Zosteracea seagrass, cultured oyster, deep learning, Mangoku Bay
Tasks	Semantic Segmentation
Published	2019-09-06
URL	https://arxiv.org/abs/1909.02747v1
PDF	https://arxiv.org/pdf/1909.02747v1.pdf
PWC	https://paperswithcode.com/paper/eelgrass-beds-and-oyster-farming-at-a-lagoon
Repo
Framework

Deep Learning-Based Quantization of L-Values for Gray-Coded Modulation


Title	Deep Learning-Based Quantization of L-Values for Gray-Coded Modulation
Authors	Marius Arvinte, Sriram Vishwanath, Ahmed H. Tewfik
Abstract	In this work, a deep learning-based quantization scheme for log-likelihood ratio (L-value) storage is introduced. We analyze the dependency between the average magnitude of different L-values from the same quadrature amplitude modulation (QAM) symbol and show they follow a consistent ordering. Based on this we design a deep autoencoder that jointly compresses and separately reconstructs each L-value, allowing the use of a weighted loss function that aims to more accurately reconstructs low magnitude inputs. Our method is shown to be competitive with state-of-the-art maximum mutual information quantization schemes, reducing the required memory footprint by a ratio of up to two and a loss of performance smaller than 0.1 dB with less than two effective bits per L-value or smaller than 0.04 dB with 2.25 effective bits. We experimentally show that our proposed method is a universal compression scheme in the sense that after training on an LDPC-coded Rayleigh fading scenario we can reuse the same network without further training on other channel models and codes while preserving the same performance benefits.
Tasks	Quantization
Published	2019-06-18
URL	https://arxiv.org/abs/1906.07849v1
PDF	https://arxiv.org/pdf/1906.07849v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-based-quantization-of-l-values
Repo
Framework

Consensus Clustering: An Embedding Perspective, Extension and Beyond


Title	Consensus Clustering: An Embedding Perspective, Extension and Beyond
Authors	Hongfu Liu, Zhiqiang Tao, Zhengming Ding
Abstract	Consensus clustering fuses diverse basic partitions (i.e., clustering results obtained from conventional clustering methods) into an integrated one, which has attracted increasing attention in both academic and industrial areas due to its robust and effective performance. Tremendous research efforts have been made to thrive this domain in terms of algorithms and applications. Although there are some survey papers to summarize the existing literature, they neglect to explore the underlying connection among different categories. Differently, in this paper we aim to provide an embedding prospective to illustrate the consensus mechanism, which transfers categorical basic partitions to other representations (e.g., binary coding, spectral embedding, etc) for the clustering purpose. To this end, we not only unify two major categories of consensus clustering, but also build an intuitive connection between consensus clustering and graph embedding. Moreover, we elaborate several extensions of classical consensus clustering from different settings and problems. Beyond this, we demonstrate how to leverage consensus clustering to address other tasks, such as constrained clustering, domain adaptation, feature selection, and outlier detection. Finally, we conclude this survey with future work in terms of interpretability, learnability and theoretical analysis.
Tasks	Domain Adaptation, Feature Selection, Graph Embedding, Outlier Detection
Published	2019-05-31
URL	https://arxiv.org/abs/1906.00120v1
PDF	https://arxiv.org/pdf/1906.00120v1.pdf
PWC	https://paperswithcode.com/paper/190600120
Repo
Framework

Discovery of Dynamics Using Linear Multistep Methods


Title	Discovery of Dynamics Using Linear Multistep Methods
Authors	Rachael Keller, Qiang Du
Abstract	Linear multistep methods (LMMs) are popular time discretization techniques for the numerical solution of differential equations. Traditionally they are applied to solve for the state given the dynamics (the forward problem), but here we consider their application for learning the dynamics given the state (the inverse problem). This repurposing of LMMs is largely motivated by growing interest in data-driven modeling of dynamics, but the behavior and analysis of LMMs for discovery turn out to be significantly different from the well-known, existing theory for the forward problem. Assuming the highly idealized setting of being given the exact state, we establish for the first time a rigorous framework based on refined notions of consistency and stability to yield convergence using LMMs for discovery. When applying these concepts to three popular M-step LMMs, the Adams-Bashforth, Adams-Moulton, and Backwards Differentiation Formula schemes, the new theory suggests that Adams-Bashforth for $1 \leq M \leq 6$, Adams-Moulton for $M=0$ and $M=1$, and Backwards Differentiation Formula for $M \in \mathbb{N}$ are convergent, and, otherwise, the methods are not convergent in general. In addition, we provide numerical experiments to both motivate and substantiate our theoretical analysis.
Tasks
Published	2019-12-29
URL	https://arxiv.org/abs/1912.12728v2
PDF	https://arxiv.org/pdf/1912.12728v2.pdf
PWC	https://paperswithcode.com/paper/discovery-of-dynamics-using-linear-multistep
Repo
Framework

Learning Semantic Neural Tree for Human Parsing


Title	Learning Semantic Neural Tree for Human Parsing
Authors	Ruyi Ji, Dawei Du, Libo Zhang, Longyin Wen, Yanjun Wu, Chen Zhao, Feiyue Huang, Siwei Lyu
Abstract	The majority of existing human parsing methods formulate the task as semantic segmentation, which regard each semantic category equally and fail to exploit the intrinsic physiological structure of human body, resulting in inaccurate results. In this paper, we design a novel semantic neural tree for human parsing, which uses a tree architecture to encode physiological structure of human body, and designs a coarse to fine process in a cascade manner to generate accurate results. Specifically, the semantic neural tree is designed to segment human regions into multiple semantic subregions (e.g., face, arms, and legs) in a hierarchical way using a new designed attention routing module. Meanwhile, we introduce the semantic aggregation module to combine multiple hierarchical features to exploit more context information for better performance. Our semantic neural tree can be trained in an end-to-end fashion by standard stochastic gradient descent (SGD) with back-propagation. Several experiments conducted on four challenging datasets for both single and multiple human parsing, i.e., LIP, PASCAL-Person-Part, CIHP and MHP-v2, demonstrate the effectiveness of the proposed method. Code can be found at https://isrc.iscas.ac.cn/gitlab/research/sematree.
Tasks	Human Parsing, Semantic Segmentation
Published	2019-12-20
URL	https://arxiv.org/abs/1912.09622v1
PDF	https://arxiv.org/pdf/1912.09622v1.pdf
PWC	https://paperswithcode.com/paper/learning-semantic-neural-tree-for-human
Repo
Framework