Paper Group ANR 1289
Fine-Grained Temporal Relation Extraction. Recent Advances in Diversified Recommendation. MindTheStep-AsyncPSGD: Adaptive Asynchronous Parallel Stochastic Gradient Descent. Restricted Isometry Property under High Correlations. Learning Two-View Correspondences and Geometry Using Order-Aware Network. Defensive Quantization: When Efficiency Meets Rob …
Fine-Grained Temporal Relation Extraction
| Title | Fine-Grained Temporal Relation Extraction |
| Authors | Siddharth Vashishtha, Benjamin Van Durme, Aaron Steven White |
| Abstract | We present a novel semantic framework for modeling temporal relations and event durations that maps pairs of events to real-valued scales. We use this framework to construct the largest temporal relations dataset to date, covering the entirety of the Universal Dependencies English Web Treebank. We use this dataset to train models for jointly predicting fine-grained temporal relations and event durations. We report strong results on our data and show the efficacy of a transfer-learning approach for predicting categorical relations. |
| Tasks | Relation Extraction, Transfer Learning |
| Published | 2019-02-04 |
| URL | https://arxiv.org/abs/1902.01390v2 |
| https://arxiv.org/pdf/1902.01390v2.pdf | |
| PWC | https://paperswithcode.com/paper/fine-grained-temporal-relation-extraction |
| Repo | |
| Framework | |
Recent Advances in Diversified Recommendation
| Title | Recent Advances in Diversified Recommendation |
| Authors | Qiong Wu, Yong Liu, Chunyan Miao, Yin Zhao, Lu Guan, Haihong Tang |
| Abstract | With the rapid development of recommender systems, accuracy is no longer the only golden criterion for evaluating whether the recommendation results are satisfying or not. In recent years, diversity has gained tremendous attention in recommender systems research, which has been recognized to be an important factor for improving user satisfaction. On the one hand, diversified recommendation helps increase the chance of answering ephemeral user needs. On the other hand, diversifying recommendation results can help the business improve product visibility and explore potential user interests. In this paper, we are going to review the recent advances in diversified recommendation. Specifically, we first review the various definitions of diversity and generate a taxonomy to shed light on how diversity have been modeled or measured in recommender systems. After that, we summarize the major optimization approaches to diversified recommendation from a taxonomic view. Last but not the least, we project into the future and point out trending research directions on this topic. |
| Tasks | Recommendation Systems |
| Published | 2019-05-16 |
| URL | https://arxiv.org/abs/1905.06589v1 |
| https://arxiv.org/pdf/1905.06589v1.pdf | |
| PWC | https://paperswithcode.com/paper/recent-advances-in-diversified-recommendation |
| Repo | |
| Framework | |
MindTheStep-AsyncPSGD: Adaptive Asynchronous Parallel Stochastic Gradient Descent
| Title | MindTheStep-AsyncPSGD: Adaptive Asynchronous Parallel Stochastic Gradient Descent |
| Authors | Karl Bäckström, Marina Papatriantafilou, Philippas Tsigas |
| Abstract | Stochastic Gradient Descent (SGD) is very useful in optimization problems with high-dimensional non-convex target functions, and hence constitutes an important component of several Machine Learning and Data Analytics methods. Recently there have been significant works on understanding the parallelism inherent to SGD, and its convergence properties. Asynchronous, parallel SGD (AsyncPSGD) has received particular attention, due to observed performance benefits. On the other hand, asynchrony implies inherent challenges in understanding the execution of the algorithm and its convergence, stemming from the fact that the contribution of a thread might be based on an old (stale) view of the state. In this work we aim to deepen the understanding of AsyncPSGD in order to increase the statistical efficiency in the presence of stale gradients. We propose new models for capturing the nature of the staleness distribution in a practical setting. Using the proposed models, we derive a staleness-adaptive SGD framework, MindTheStep-AsyncPSGD, for adapting the step size in an online-fashion, which provably reduces the negative impact of asynchrony. Moreover, we provide general convergence time bounds for a wide class of staleness-adaptive step size strategies for convex target functions. We also provide a detailed empirical study, showing how our approach implies faster convergence for deep learning applications. |
| Tasks | |
| Published | 2019-11-08 |
| URL | https://arxiv.org/abs/1911.03444v1 |
| https://arxiv.org/pdf/1911.03444v1.pdf | |
| PWC | https://paperswithcode.com/paper/mindthestep-asyncpsgd-adaptive-asynchronous |
| Repo | |
| Framework | |
Restricted Isometry Property under High Correlations
| Title | Restricted Isometry Property under High Correlations |
| Authors | Shiva Prasad Kasiviswanathan, Mark Rudelson |
| Abstract | Matrices satisfying the Restricted Isometry Property (RIP) play an important role in the areas of compressed sensing and statistical learning. RIP matrices with optimal parameters are mainly obtained via probabilistic arguments, as explicit constructions seem hard. It is therefore interesting to ask whether a fixed matrix can be incorporated into a construction of restricted isometries. In this paper, we construct a new broad ensemble of random matrices with dependent entries that satisfy the restricted isometry property. Our construction starts with a fixed (deterministic) matrix $X$ satisfying some simple stable rank condition, and we show that the matrix $XR$, where $R$ is a random matrix drawn from various popular probabilistic models (including, subgaussian, sparse, low-randomness, satisfying convex concentration property), satisfies the RIP with high probability. These theorems have various applications in signal recovery, random matrix theory, dimensionality reduction, etc. Additionally, motivated by an application for understanding the effectiveness of word vector embeddings popular in natural language processing and machine learning applications, we investigate the RIP of the matrix $XR^{(l)}$ where $R^{(l)}$ is formed by taking all possible (disregarding order) $l$-way entrywise products of the columns of a random matrix $R$. |
| Tasks | Dimensionality Reduction |
| Published | 2019-04-11 |
| URL | https://arxiv.org/abs/1904.05510v2 |
| https://arxiv.org/pdf/1904.05510v2.pdf | |
| PWC | https://paperswithcode.com/paper/restricted-isometry-property-under-high |
| Repo | |
| Framework | |
Learning Two-View Correspondences and Geometry Using Order-Aware Network
| Title | Learning Two-View Correspondences and Geometry Using Order-Aware Network |
| Authors | Jiahui Zhang, Dawei Sun, Zixin Luo, Anbang Yao, Lei Zhou, Tianwei Shen, Yurong Chen, Long Quan, Hongen Liao |
| Abstract | Establishing correspondences between two images requires both local and global spatial context. Given putative correspondences of feature points in two views, in this paper, we propose Order-Aware Network, which infers the probabilities of correspondences being inliers and regresses the relative pose encoded by the essential matrix. Specifically, this proposed network is built hierarchically and comprises three novel operations. First, to capture the local context of sparse correspondences, the network clusters unordered input correspondences by learning a soft assignment matrix. These clusters are in a canonical order and invariant to input permutations. Next, the clusters are spatially correlated to form the global context of correspondences. After that, the context-encoded clusters are recovered back to the original size through a proposed upsampling operator. We intensively experiment on both outdoor and indoor datasets. The accuracy of the two-view geometry and correspondences are significantly improved over the state-of-the-arts. Code will be available at https://github.com/zjhthu/OANet.git. |
| Tasks | |
| Published | 2019-08-14 |
| URL | https://arxiv.org/abs/1908.04964v1 |
| https://arxiv.org/pdf/1908.04964v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-two-view-correspondences-and |
| Repo | |
| Framework | |
Defensive Quantization: When Efficiency Meets Robustness
| Title | Defensive Quantization: When Efficiency Meets Robustness |
| Authors | Ji Lin, Chuang Gan, Song Han |
| Abstract | Neural network quantization is becoming an industry standard to efficiently deploy deep learning models on hardware platforms, such as CPU, GPU, TPU, and FPGAs. However, we observe that the conventional quantization approaches are vulnerable to adversarial attacks. This paper aims to raise people’s awareness about the security of the quantized models, and we designed a novel quantization methodology to jointly optimize the efficiency and robustness of deep learning models. We first conduct an empirical study to show that vanilla quantization suffers more from adversarial attacks. We observe that the inferior robustness comes from the error amplification effect, where the quantization operation further enlarges the distance caused by amplified noise. Then we propose a novel Defensive Quantization (DQ) method by controlling the Lipschitz constant of the network during quantization, such that the magnitude of the adversarial noise remains non-expansive during inference. Extensive experiments on CIFAR-10 and SVHN datasets demonstrate that our new quantization method can defend neural networks against adversarial examples, and even achieves superior robustness than their full-precision counterparts while maintaining the same hardware efficiency as vanilla quantization approaches. As a by-product, DQ can also improve the accuracy of quantized models without adversarial attack. |
| Tasks | Adversarial Attack, Quantization |
| Published | 2019-04-17 |
| URL | http://arxiv.org/abs/1904.08444v1 |
| http://arxiv.org/pdf/1904.08444v1.pdf | |
| PWC | https://paperswithcode.com/paper/defensive-quantization-when-efficiency-meets-1 |
| Repo | |
| Framework | |
Making Study Populations Visible through Knowledge Graphs
| Title | Making Study Populations Visible through Knowledge Graphs |
| Authors | Shruthi Chari, Miao Qi, Nkcheniyere N. Agu, Oshani Seneviratne, James P. McCusker, Kristin P. Bennett, Amar K. Das, Deborah L. McGuinness |
| Abstract | Treatment recommendations within Clinical Practice Guidelines (CPGs) are largely based on findings from clinical trials and case studies, referred to here as research studies, that are often based on highly selective clinical populations, referred to here as study cohorts. When medical practitioners apply CPG recommendations, they need to understand how well their patient population matches the characteristics of those in the study cohort, and thus are confronted with the challenges of locating the study cohort information and making an analytic comparison. To address these challenges, we develop an ontology-enabled prototype system, which exposes the population descriptions in research studies in a declarative manner, with the ultimate goal of allowing medical practitioners to better understand the applicability and generalizability of treatment recommendations. We build a Study Cohort Ontology (SCO) to encode the vocabulary of study population descriptions, that are often reported in the first table in the published work, thus they are often referred to as Table 1. We leverage the well-used Semanticscience Integrated Ontology (SIO) for defining property associations between classes. Further, we model the key components of Table 1s, i.e., collections of study subjects, subject characteristics, and statistical measures in RDF knowledge graphs. We design scenarios for medical practitioners to perform population analysis, and generate cohort similarity visualizations to determine the applicability of a study population to the clinical population of interest. Our semantic approach to make study populations visible, by standardized representations of Table 1s, allows users to quickly derive clinically relevant inferences about study populations. |
| Tasks | Knowledge Graphs |
| Published | 2019-07-09 |
| URL | https://arxiv.org/abs/1907.04358v1 |
| https://arxiv.org/pdf/1907.04358v1.pdf | |
| PWC | https://paperswithcode.com/paper/making-study-populations-visible-through |
| Repo | |
| Framework | |
On Class Imbalance and Background Filtering in Visual Relationship Detection
| Title | On Class Imbalance and Background Filtering in Visual Relationship Detection |
| Authors | Alessio Sarullo, Tingting Mu |
| Abstract | In this paper we investigate the problems of class imbalance and irrelevant relationships in Visual Relationship Detection (VRD). State-of-the-art deep VRD models still struggle to predict uncommon classes, limiting their applicability. Moreover, many methods are incapable of properly filtering out background relationships while predicting relevant ones. Although these problems are very apparent, they have both been overlooked so far. We analyse why this is the case and propose modifications to both model and training to alleviate the aforementioned issues, as well as suggesting new measures to complement existing ones and give a more holistic picture of the efficacy of a model. |
| Tasks | |
| Published | 2019-03-20 |
| URL | http://arxiv.org/abs/1903.08456v2 |
| http://arxiv.org/pdf/1903.08456v2.pdf | |
| PWC | https://paperswithcode.com/paper/on-class-imbalance-and-background-filtering |
| Repo | |
| Framework | |
Unification of Template-Expansion and XML-Validation
| Title | Unification of Template-Expansion and XML-Validation |
| Authors | René Haberland |
| Abstract | The processing of XML documents often includes creation and validation. These two operations are typically performed in two different nodes within a computer network that do not correlate with each other. The process of creation is also called instantiation of a template and can be described by filling a template with data from external repositories. Initial access to arbitrary sources can be formulated as an expression of certain command languages like XPath. Filling means copying invariant element nodes to the target document and unfolding variable parts from a given template. Validation is a descision problem returning true if a given XML document satisfies a schema and false otherwise. The main subject is to find a language that unions the template expansion and the validation. [..]. |
| Tasks | |
| Published | 2019-06-19 |
| URL | https://arxiv.org/abs/1906.08369v1 |
| https://arxiv.org/pdf/1906.08369v1.pdf | |
| PWC | https://paperswithcode.com/paper/unification-of-template-expansion-and-xml |
| Repo | |
| Framework | |
Mixed High-Order Attention Network for Person Re-Identification
| Title | Mixed High-Order Attention Network for Person Re-Identification |
| Authors | Binghui Chen, Weihong Deng, Jiani Hu |
| Abstract | Attention has become more attractive in person reidentification (ReID) as it is capable of biasing the allocation of available resources towards the most informative parts of an input signal. However, state-of-the-art works concentrate only on coarse or first-order attention design, e.g. spatial and channels attention, while rarely exploring higher-order attention mechanism. We take a step towards addressing this problem. In this paper, we first propose the High-Order Attention (HOA) module to model and utilize the complex and high-order statistics information in attention mechanism, so as to capture the subtle differences among pedestrians and to produce the discriminative attention proposals. Then, rethinking person ReID as a zero-shot learning problem, we propose the Mixed High-Order Attention Network (MHN) to further enhance the discrimination and richness of attention knowledge in an explicit manner. Extensive experiments have been conducted to validate the superiority of our MHN for person ReID over a wide variety of state-of-the-art methods on three large-scale datasets, including Market-1501, DukeMTMC-ReID and CUHK03-NP. Code is available at http://www.bhchen.cn/. |
| Tasks | Person Re-Identification, Zero-Shot Learning |
| Published | 2019-08-16 |
| URL | https://arxiv.org/abs/1908.05819v1 |
| https://arxiv.org/pdf/1908.05819v1.pdf | |
| PWC | https://paperswithcode.com/paper/mixed-high-order-attention-network-for-person |
| Repo | |
| Framework | |
IntrinSeqNet: Learning to Estimate the Reflectance from Varying Illumination
| Title | IntrinSeqNet: Learning to Estimate the Reflectance from Varying Illumination |
| Authors | Grégoire Nieto, Mohammad Rouhani, Philippe Robert |
| Abstract | Intrinsic image decomposition describes an image based on its reflectance and shading components. In this paper we tackle the problem of estimating the diffuse reflectance from a sequence of images captured from a fixed viewpoint under various illuminations. To this end we propose a deep learning approach to avoid heuristics and strong assumptions on the reflectance prior. We compare two network architectures: one classic ‘U’ shaped Convolutional Neural Network (CNN) and a Recurrent Neural Network (RNN) composed of Convolutional Gated Recurrent Units (CGRU). We train our networks on a new dataset specifically designed for the task of intrinsic decomposition from sequences. We test our networks on MIT and BigTime datasets and outperform state-of-the-art algorithms both qualitatively and quantitatively. |
| Tasks | Intrinsic Image Decomposition |
| Published | 2019-06-13 |
| URL | https://arxiv.org/abs/1906.05893v1 |
| https://arxiv.org/pdf/1906.05893v1.pdf | |
| PWC | https://paperswithcode.com/paper/intrinseqnet-learning-to-estimate-the |
| Repo | |
| Framework | |
Separate In Latent Space: Unsupervised Single Image Layer Separation
| Title | Separate In Latent Space: Unsupervised Single Image Layer Separation |
| Authors | Yunfei Liu, Feng Lu |
| Abstract | Many real world vision tasks, such as reflection removal from a transparent surface and intrinsic image decomposition, can be modeled as single image layer separation. However, this problem is highly ill-posed, requiring accurately aligned and hard to collect triplet data to train the CNN models. To address this problem, this paper proposes an unsupervised method that requires no ground truth data triplet in training. At the core of the method are two assumptions about data distributions in the latent spaces of different layers, based on which a novel unsupervised layer separation pipeline can be derived. Then the method can be constructed based on the GANs framework with self-supervision and cycle consistency constraints, etc. Experimental results demonstrate its successfulness in outperforming existing unsupervised methods in both synthetic and real world tasks. The method also shows its ability to solve a more challenging multi-layer separation task. |
| Tasks | Intrinsic Image Decomposition |
| Published | 2019-06-03 |
| URL | https://arxiv.org/abs/1906.00734v3 |
| https://arxiv.org/pdf/1906.00734v3.pdf | |
| PWC | https://paperswithcode.com/paper/190600734 |
| Repo | |
| Framework | |
Getting To Know You: User Attribute Extraction from Dialogues
| Title | Getting To Know You: User Attribute Extraction from Dialogues |
| Authors | Chien-Sheng Wu, Andrea Madotto, Zhaojiang Lin, Peng Xu, Pascale Fung |
| Abstract | User attributes provide rich and useful information for user understanding, yet structured and easy-to-use attributes are often sparsely populated. In this paper, we leverage dialogues with conversational agents, which contain strong suggestions of user information, to automatically extract user attributes. Since no existing dataset is available for this purpose, we apply distant supervision to train our proposed two-stage attribute extractor, which surpasses several retrieval and generation baselines on human evaluation. Meanwhile, we discuss potential applications (e.g., personalized recommendation and dialogue systems) of such extracted user attributes, and point out current limitations to cast light on future work. |
| Tasks | |
| Published | 2019-08-13 |
| URL | https://arxiv.org/abs/1908.04621v1 |
| https://arxiv.org/pdf/1908.04621v1.pdf | |
| PWC | https://paperswithcode.com/paper/getting-to-know-you-user-attribute-extraction |
| Repo | |
| Framework | |
Semantic Hierarchical Priors for Intrinsic Image Decomposition
| Title | Semantic Hierarchical Priors for Intrinsic Image Decomposition |
| Authors | Saurabh Saini, P. J. Narayanan |
| Abstract | Intrinsic Image Decomposition (IID) is a challenging and interesting computer vision problem with various applications in several fields. We present novel semantic priors and an integrated approach for single image IID that involves analyzing image at three hierarchical context levels. Local context priors capture scene properties at each pixel within a small neighbourhood. Mid-level context priors encode object level semantics. Global context priors establish correspondences at the scene level. Our semantic priors are designed on both fixed and flexible regions, using selective search method and Convolutional Neural Network features. Our IID method is an iterative multistage optimization scheme and consists of two complementary formulations: $L_2$ smoothing for shading and $L_1$ sparsity for reflectance. Experiments and analysis of our method indicate the utility of our semantic priors and structured hierarchical analysis in an IID framework. We compare our method with other contemporary IID solutions and show results with lesser artifacts. Finally, we highlight that proper choice and encoding of prior knowledge can produce competitive results even when compared to end-to-end deep learning IID methods, signifying the importance of such priors. We believe that the insights and techniques presented in this paper would be useful in the future IID research. |
| Tasks | Intrinsic Image Decomposition |
| Published | 2019-02-11 |
| URL | https://arxiv.org/abs/1902.03830v2 |
| https://arxiv.org/pdf/1902.03830v2.pdf | |
| PWC | https://paperswithcode.com/paper/semantic-hierarchical-priors-for-intrinsic |
| Repo | |
| Framework | |
WIDER Face and Pedestrian Challenge 2018: Methods and Results
| Title | WIDER Face and Pedestrian Challenge 2018: Methods and Results |
| Authors | Chen Change Loy, Dahua Lin, Wanli Ouyang, Yuanjun Xiong, Shuo Yang, Qingqiu Huang, Dongzhan Zhou, Wei Xia, Quanquan Li, Ping Luo, Junjie Yan, Jianfeng Wang, Zuoxin Li, Ye Yuan, Boxun Li, Shuai Shao, Gang Yu, Fangyun Wei, Xiang Ming, Dong Chen, Shifeng Zhang, Cheng Chi, Zhen Lei, Stan Z. Li, Hongkai Zhang, Bingpeng Ma, Hong Chang, Shiguang Shan, Xilin Chen, Wu Liu, Boyan Zhou, Huaxiong Li, Peng Cheng, Tao Mei, Artem Kukharenko, Artem Vasenin, Nikolay Sergievskiy, Hua Yang, Liangqi Li, Qiling Xu, Yuan Hong, Lin Chen, Mingjun Sun, Yirong Mao, Shiying Luo, Yongjun Li, Ruiping Wang, Qiaokang Xie, Ziyang Wu, Lei Lu, Yiheng Liu, Wengang Zhou |
| Abstract | This paper presents a review of the 2018 WIDER Challenge on Face and Pedestrian. The challenge focuses on the problem of precise localization of human faces and bodies, and accurate association of identities. It comprises of three tracks: (i) WIDER Face which aims at soliciting new approaches to advance the state-of-the-art in face detection, (ii) WIDER Pedestrian which aims to find effective and efficient approaches to address the problem of pedestrian detection in unconstrained environments, and (iii) WIDER Person Search which presents an exciting challenge of searching persons across 192 movies. In total, 73 teams made valid submissions to the challenge tracks. We summarize the winning solutions for all three tracks. and present discussions on open problems and potential research directions in these topics. |
| Tasks | Face Detection, Pedestrian Detection, Person Search |
| Published | 2019-02-19 |
| URL | http://arxiv.org/abs/1902.06854v1 |
| http://arxiv.org/pdf/1902.06854v1.pdf | |
| PWC | https://paperswithcode.com/paper/wider-face-and-pedestrian-challenge-2018 |
| Repo | |
| Framework | |
