January 26, 2020

2874 words 14 mins read

Paper Group ANR 1527

Patent Analytics Based on Feature Vector Space Model: A Case of IoT. Playing log(N)-Questions over Sentences. HAR-Net: Joint Learning of Hybrid Attention for Single-stage Object Detection. Recovering the parameters underlying the Lorenz-96 chaotic dynamics. Machine-learning based three-qubit gate for realization of a Toffoli gate with cQED-based tr …

Patent Analytics Based on Feature Vector Space Model: A Case of IoT


Title	Patent Analytics Based on Feature Vector Space Model: A Case of IoT
Authors	Lei Lei, Jiaju Qi, Kan Zheng
Abstract	The number of approved patents worldwide increases rapidly each year, which requires new patent analytics to efficiently mine the valuable information attached to these patents. Vector space model (VSM) represents documents as high-dimensional vectors, where each dimension corresponds to a unique term. While originally proposed for information retrieval systems, VSM has also seen wide applications in patent analytics, and used as a fundamental tool to map patent documents to structured data. However, VSM method suffers from several limitations when applied to patent analysis tasks, such as loss of sentence-level semantics and curse-of-dimensionality problems. In order to address the above limitations, we propose a patent analytics based on feature vector space model (FVSM), where the FVSM is constructed by mapping patent documents to feature vectors extracted by convolutional neural networks (CNN). The applications of FVSM for three typical patent analysis tasks, i.e., patents similarity comparison, patent clustering, and patent map generation are discussed. A case study using patents related to Internet of Things (IoT) technology is illustrated to demonstrate the performance and effectiveness of FVSM. The proposed FVSM can be adopted by other patent analysis studies to replace VSM, based on which various big data learning tasks can be performed.
Tasks	Information Retrieval
Published	2019-04-17
URL	http://arxiv.org/abs/1904.08100v1
PDF	http://arxiv.org/pdf/1904.08100v1.pdf
PWC	https://paperswithcode.com/paper/patent-analytics-based-on-feature-vector
Repo
Framework

Playing log(N)-Questions over Sentences


Title	Playing log(N)-Questions over Sentences
Authors	Peter Potash, Kaheer Suleman
Abstract	We propose a two-agent game wherein a questioner must be able to conjure discerning questions between sentences, incorporate responses from an answerer, and keep track of a hypothesis state. The questioner must be able to understand the information required to make its final guess, while also being able to reason over the game’s text environment based on the answerer’s responses. We experiment with an end-to-end model where both agents can learn simultaneously to play the game, showing that simultaneously achieving high game accuracy and producing meaningful questions can be a difficult trade-off.
Tasks
Published	2019-08-13
URL	https://arxiv.org/abs/1908.04660v1
PDF	https://arxiv.org/pdf/1908.04660v1.pdf
PWC	https://paperswithcode.com/paper/playing-logn-questions-over-sentences
Repo
Framework

HAR-Net: Joint Learning of Hybrid Attention for Single-stage Object Detection


Title	HAR-Net: Joint Learning of Hybrid Attention for Single-stage Object Detection
Authors	Ya-Li Li, Shengjin Wang
Abstract	Object detection has been a challenging task in computer vision. Although significant progress has been made in object detection with deep neural networks, the attention mechanism is far from development. In this paper, we propose the hybrid attention mechanism for single-stage object detection. First, we present the modules of spatial attention, channel attention and aligned attention for single-stage object detection. In particular, stacked dilated convolution layers with symmetrically fixed rates are constructed to learn spatial attention. The channel attention is proposed with the cross-level group normalization and squeeze-and-excitation module. Aligned attention is constructed with organized deformable filters. Second, the three kinds of attention are unified to construct the hybrid attention mechanism. We then embed the hybrid attention into Retina-Net and propose the efficient single-stage HAR-Net for object detection. The attention modules and the proposed HAR-Net are evaluated on the COCO detection dataset. Experiments demonstrate that hybrid attention can significantly improve the detection accuracy and the HAR-Net can achieve the state-of-the-art 45.8% mAP, outperform existing single-stage object detectors.
Tasks	Object Detection
Published	2019-04-25
URL	http://arxiv.org/abs/1904.11141v1
PDF	http://arxiv.org/pdf/1904.11141v1.pdf
PWC	https://paperswithcode.com/paper/har-net-joint-learning-of-hybrid-attention
Repo
Framework

Recovering the parameters underlying the Lorenz-96 chaotic dynamics


Title	Recovering the parameters underlying the Lorenz-96 chaotic dynamics
Authors	Soukayna Mouatadid, Pierre Gentine, Wei Yu, Steve Easterbrook
Abstract	Climate projections suffer from uncertain equilibrium climate sensitivity. The reason behind this uncertainty is the resolution of global climate models, which is too coarse to resolve key processes such as clouds and convection. These processes are approximated using heuristics in a process called parameterization. The selection of these parameters can be subjective, leading to significant uncertainties in the way clouds are represented in global climate models. Here, we explore three deep network algorithms to infer these parameters in an objective and data-driven way. We compare the performance of a fully-connected network, a one-dimensional and, a two-dimensional convolutional networks to recover the underlying parameters of the Lorenz-96 model, a non-linear dynamical system that has similar behavior to the climate system.
Tasks
Published	2019-06-16
URL	https://arxiv.org/abs/1906.06786v1
PDF	https://arxiv.org/pdf/1906.06786v1.pdf
PWC	https://paperswithcode.com/paper/recovering-the-parameters-underlying-the
Repo
Framework

Machine-learning based three-qubit gate for realization of a Toffoli gate with cQED-based transmon systems


Title	Machine-learning based three-qubit gate for realization of a Toffoli gate with cQED-based transmon systems
Authors	Sahar Daraeizadeh, Shavindra P. Premaratne, Xiaoyu Song, Marek Perkowski, Anne Y. Matsuura
Abstract	We use machine learning techniques to design a 50 ns three-qubit flux-tunable controlled-controlled-phase gate with fidelity of >99.99% for nearest-neighbor coupled transmons in circuit quantum electrodynamics architectures. We explain our gate design procedure where we enforce realistic constraints, and analyze the new gate’s robustness under decoherence, distortion, and random noise. Our controlled-controlled-phase gate in combination with two single-qubit gates realizes a Toffoli gate which is widely used in quantum circuits, logic synthesis, quantum error correction, and quantum games.
Tasks
Published	2019-08-02
URL	https://arxiv.org/abs/1908.01092v1
PDF	https://arxiv.org/pdf/1908.01092v1.pdf
PWC	https://paperswithcode.com/paper/machine-learning-based-three-qubit-gate-for
Repo
Framework

Lossless Compression for 3DCNNs Based on Tensor Train Decomposition


Title	Lossless Compression for 3DCNNs Based on Tensor Train Decomposition
Authors	Dingheng Wang, Guangshe Zhao, Guoqi Li, Lei Deng, Yang Wu
Abstract	Three dimensional convolutional neural networks (3DCNNs) have been applied in many tasks of video or 3D point cloud recognition. However, due to the higher dimension of convolutional kernels, the space complexity of 3DCNNs is generally larger than that of traditional two dimensional convolutional neural networks (2DCNNs). To miniaturize 3DCNNs for the deployment in confining environments such as embedded devices, neural network compression is a promising approach. In this work, we adopt the tensor train (TT) decomposition, the most compact and simplest \emph{in situ} training compression method, to shrink the 3DCNN models. We give the tensorizing for 3D convolutional kernels in TT format and investigate how to select appropriate ranks for the tensor in TT format. In the light of multiple contrast experiments based on VIVA challenge and UCF11 datasets, we conclude that the TT decomposition can compress redundant 3DCNNs in a ratio up to 121(\times) with little accuracy improvement. Besides, we achieve a state-of-the-art result of TT-3DCNN on VIVA challenge dataset (81.83%).
Tasks	Neural Network Compression
Published	2019-12-08
URL	https://arxiv.org/abs/1912.03647v1
PDF	https://arxiv.org/pdf/1912.03647v1.pdf
PWC	https://paperswithcode.com/paper/lossless-compression-for-3dcnns-based-on
Repo
Framework

Graph Generation with Variational Recurrent Neural Network


Title	Graph Generation with Variational Recurrent Neural Network
Authors	Shih-Yang Su, Hossein Hajimirsadeghi, Greg Mori
Abstract	Generating graph structures is a challenging problem due to the diverse representations and complex dependencies among nodes. In this paper, we introduce Graph Variational Recurrent Neural Network (GraphVRNN), a probabilistic autoregressive model for graph generation. Through modeling the latent variables of graph data, GraphVRNN can capture the joint distributions of graph structures and the underlying node attributes. We conduct experiments on the proposed GraphVRNN in both graph structure learning and attribute generation tasks. The evaluation results show that the variational component allows our network to model complicated distributions, as well as generate plausible structures and node attributes.
Tasks	Graph Generation
Published	2019-10-02
URL	https://arxiv.org/abs/1910.01743v1
PDF	https://arxiv.org/pdf/1910.01743v1.pdf
PWC	https://paperswithcode.com/paper/graph-generation-with-variational-recurrent
Repo
Framework

Simultaneously Linking Entities and Extracting Relations from Biomedical Text Without Mention-level Supervision


Title	Simultaneously Linking Entities and Extracting Relations from Biomedical Text Without Mention-level Supervision
Authors	Trapit Bansal, Pat Verga, Neha Choudhary, Andrew McCallum
Abstract	Understanding the meaning of text often involves reasoning about entities and their relationships. This requires identifying textual mentions of entities, linking them to a canonical concept, and discerning their relationships. These tasks are nearly always viewed as separate components within a pipeline, each requiring a distinct model and training data. While relation extraction can often be trained with readily available weak or distant supervision, entity linkers typically require expensive mention-level supervision – which is not available in many domains. Instead, we propose a model which is trained to simultaneously produce entity linking and relation decisions while requiring no mention-level annotations. This approach avoids cascading errors that arise from pipelined methods and more accurately predicts entity relationships from text. We show that our model outperforms a state-of-the art entity linking and relation extraction pipeline on two biomedical datasets and can drastically improve the overall recall of the system.
Tasks	Entity Linking, Relation Extraction
Published	2019-12-02
URL	https://arxiv.org/abs/1912.01070v1
PDF	https://arxiv.org/pdf/1912.01070v1.pdf
PWC	https://paperswithcode.com/paper/simultaneously-linking-entities-and
Repo
Framework

DCT-CompCNN: A Novel Image Classification Network Using JPEG Compressed DCT Coefficients


Title	DCT-CompCNN: A Novel Image Classification Network Using JPEG Compressed DCT Coefficients
Authors	Bulla Rajesh, Mohammed Javed, Ratnesh, Shubham Srivastava
Abstract	The popularity of Convolutional Neural Network (CNN) in the field of Image Processing and Computer Vision has motivated researchers and industrialist experts across the globe to solve different challenges with high accuracy. The simplest way to train a CNN classifier is to directly feed the original RGB pixels images into the network. However, if we intend to classify images directly with its compressed data, the same approach may not work better, like in case of JPEG compressed images. This research paper investigates the issues of modifying the input representation of the JPEG compressed data, and then feeding into the CNN. The architecture is termed as DCT-CompCNN. This novel approach has shown that CNNs can also be trained with JPEG compressed DCT coefficients, and subsequently can produce a better performance in comparison with the conventional CNN approach. The efficiency of the modified input representation is tested with the existing ResNet-50 architecture and the proposed DCT-CompCNN architecture on a public image classification datasets like Dog Vs Cat and CIFAR-10 datasets, reporting a better performance
Tasks	Image Classification
Published	2019-07-26
URL	https://arxiv.org/abs/1907.11503v1
PDF	https://arxiv.org/pdf/1907.11503v1.pdf
PWC	https://paperswithcode.com/paper/dct-compcnn-a-novel-image-classification
Repo
Framework

All-Weather Deep Outdoor Lighting Estimation


Title	All-Weather Deep Outdoor Lighting Estimation
Authors	Jinsong Zhang, Kalyan Sunkavalli, Yannick Hold-Geoffroy, Sunil Hadap, Jonathan Eisenmann, Jean-François Lalonde
Abstract	We present a neural network that predicts HDR outdoor illumination from a single LDR image. At the heart of our work is a method to accurately learn HDR lighting from LDR panoramas under any weather condition. We achieve this by training another CNN (on a combination of synthetic and real images) to take as input an LDR panorama, and regress the parameters of the Lalonde-Matthews outdoor illumination model. This model is trained such that it a) reconstructs the appearance of the sky, and b) renders the appearance of objects lit by this illumination. We use this network to label a large-scale dataset of LDR panoramas with lighting parameters and use them to train our single image outdoor lighting estimation network. We demonstrate, via extensive experiments, that both our panorama and single image networks outperform the state of the art, and unlike prior work, are able to handle weather conditions ranging from fully sunny to overcast skies.
Tasks
Published	2019-06-12
URL	https://arxiv.org/abs/1906.04909v1
PDF	https://arxiv.org/pdf/1906.04909v1.pdf
PWC	https://paperswithcode.com/paper/all-weather-deep-outdoor-lighting-estimation-1
Repo
Framework

Spam filtering on forums: A synthetic oversampling based approach for imbalanced data classification


Title	Spam filtering on forums: A synthetic oversampling based approach for imbalanced data classification
Authors	Pratik Ratadiya, Rahul Moorthy
Abstract	Forums play an important role in providing a platform for community interaction. The introduction of irrelevant content or spam by individuals for commercial and social gains tends to degrade the professional experience presented to the forum users. Automated moderation of the relevancy of posted content is desired. Machine learning is used for text classification and finds applications in spam email detection, fraudulent transaction detection etc. The balance of classes in training data is essential in the case of classification algorithms to make the learning efficient and accurate. However, in the case of forums, the spam content is sparse compared to the relevant content giving rise to a bias towards the latter while training. A model trained on such biased data will fail to classify a spam sample. An approach based on Synthetic Minority Over-sampling Technique(SMOTE) is presented in this paper to tackle imbalanced training data. It involves synthetically creating new minority class samples from the existing ones until balance in data is achieved. The enhanced data is then passed through various classifiers for which the performance is recorded. The results were analyzed on the data of forums of Spoken Tutorial, IIT Bombay over standard performance metrics and revealed that models trained after Synthetic Minority oversampling outperform the ones trained on imbalanced data by substantial margins. An empirical comparison of the results obtained by both SMOTE and without SMOTE for various supervised classification algorithms have been presented in this paper. Synthetic oversampling proves to be a critical technique for achieving uniform class distribution which in turn yields commendable results in text classification. The presented approach can be further extended to content categorization on educational websites thus helping to improve the overall digital learning experience.
Tasks	Text Classification
Published	2019-09-10
URL	https://arxiv.org/abs/1909.04826v1
PDF	https://arxiv.org/pdf/1909.04826v1.pdf
PWC	https://paperswithcode.com/paper/spam-filtering-on-forums-a-synthetic
Repo
Framework

Robust breast cancer detection in mammography and digital breast tomosynthesis using annotation-efficient deep learning approach


Title	Robust breast cancer detection in mammography and digital breast tomosynthesis using annotation-efficient deep learning approach
Authors	William Lotter, Abdul Rahman Diab, Bryan Haslam, Jiye G. Kim, Giorgia Grisot, Eric Wu, Kevin Wu, Jorge Onieva Onieva, Jerrold L. Boxerman, Meiyun Wang, Mack Bandler, Gopal Vijayaraghavan, A. Gregory Sorensen
Abstract	Breast cancer remains a global challenge, causing over 1 million deaths globally in 2018. To achieve earlier breast cancer detection, screening x-ray mammography is recommended by health organizations worldwide and has been estimated to decrease breast cancer mortality by 20-40%. Nevertheless, significant false positive and false negative rates, as well as high interpretation costs, leave opportunities for improving quality and access. To address these limitations, there has been much recent interest in applying deep learning to mammography; however, obtaining large amounts of annotated data poses a challenge for training deep learning models for this purpose, as does ensuring generalization beyond the populations represented in the training dataset. Here, we present an annotation-efficient deep learning approach that 1) achieves state-of-the-art performance in mammogram classification, 2) successfully extends to digital breast tomosynthesis (DBT; “3D mammography”), 3) detects cancers in clinically-negative prior mammograms of cancer patients, 4) generalizes well to a population with low screening rates, and 5) outperforms five-out-of-five full-time breast imaging specialists by improving absolute sensitivity by an average of 14%. Our results demonstrate promise towards software that can improve the accuracy of and access to screening mammography worldwide.
Tasks	Breast Cancer Detection
Published	2019-12-23
URL	https://arxiv.org/abs/1912.11027v2
PDF	https://arxiv.org/pdf/1912.11027v2.pdf
PWC	https://paperswithcode.com/paper/robust-breast-cancer-detection-in-mammography
Repo
Framework

Probabilistic Category-Level Pose Estimation via Segmentation and Predicted-Shape Priors


Title	Probabilistic Category-Level Pose Estimation via Segmentation and Predicted-Shape Priors
Authors	Benjamin Burchfiel, George Konidaris
Abstract	We introduce a new method for category-level pose estimation which produces a distribution over predicted poses by integrating 3D shape estimates from a generative object model with segmentation information. Given an input depth-image of an object, our variable-time method uses a mixture density network architecture to produce a multi-modal distribution over 3DOF poses; this distribution is then combined with a prior probability encouraging silhouette agreement between the observed input and predicted object pose. Our approach significantly outperforms the current state-of-the-art in category-level 3DOF pose estimation—which outputs a point estimate and does not explicitly incorporate shape and segmentation information—as measured on the Pix3D and ShapeNet datasets.
Tasks	Pose Estimation
Published	2019-05-28
URL	https://arxiv.org/abs/1905.12079v1
PDF	https://arxiv.org/pdf/1905.12079v1.pdf
PWC	https://paperswithcode.com/paper/probabilistic-category-level-pose-estimation
Repo
Framework

Using Whole Document Context in Neural Machine Translation


Title	Using Whole Document Context in Neural Machine Translation
Authors	Valentin Macé, Christophe Servan
Abstract	In Machine Translation, considering the document as a whole can help to resolve ambiguities and inconsistencies. In this paper, we propose a simple yet promising approach to add contextual information in Neural Machine Translation. We present a method to add source context that capture the whole document with accurate boundaries, taking every word into account. We provide this additional information to a Transformer model and study the impact of our method on three language pairs. The proposed approach obtains promising results in the English-German, English-French and French-English document-level translation tasks. We observe interesting cross-sentential behaviors where the model learns to use document-level information to improve translation coherence.
Tasks	Machine Translation
Published	2019-10-16
URL	https://arxiv.org/abs/1910.07481v1
PDF	https://arxiv.org/pdf/1910.07481v1.pdf
PWC	https://paperswithcode.com/paper/using-whole-document-context-in-neural
Repo
Framework

Observational Overfitting in Reinforcement Learning


Title	Observational Overfitting in Reinforcement Learning
Authors	Xingyou Song, Yiding Jiang, Stephen Tu, Yilun Du, Behnam Neyshabur
Abstract	A major component of overfitting in model-free reinforcement learning (RL) involves the case where the agent may mistakenly correlate reward with certain spurious features from the observations generated by the Markov Decision Process (MDP). We provide a general framework for analyzing this scenario, which we use to design multiple synthetic benchmarks from only modifying the observation space of an MDP. When an agent overfits to different observation spaces even if the underlying MDP dynamics is fixed, we term this observational overfitting. Our experiments expose intriguing properties especially with regards to implicit regularization, and also corroborate results from previous works in RL generalization and supervised learning (SL).
Tasks
Published	2019-12-06
URL	https://arxiv.org/abs/1912.02975v2
PDF	https://arxiv.org/pdf/1912.02975v2.pdf
PWC	https://paperswithcode.com/paper/observational-overfitting-in-reinforcement-1
Repo
Framework