July 29, 2019

3233 words 16 mins read

Paper Group AWR 156

Familia: An Open-Source Toolkit for Industrial Topic Modeling. NegBio: a high-performance tool for negation and uncertainty detection in radiology reports. Crowdsourcing for Beyond Polarity Sentiment Analysis A Pure Emotion Lexicon. Scattertext: a Browser-Based Tool for Visualizing how Corpora Differ. Language Identification Using Deep Convolutiona …

Familia: An Open-Source Toolkit for Industrial Topic Modeling


Title	Familia: An Open-Source Toolkit for Industrial Topic Modeling
Authors	Di Jiang, Zeyu Chen, Rongzhong Lian, Siqi Bao, Chen Li
Abstract	Familia is an open-source toolkit for pragmatic topic modeling in industry. Familia abstracts the utilities of topic modeling in industry as two paradigms: semantic representation and semantic matching. Efficient implementations of the two paradigms are made publicly available for the first time. Furthermore, we provide off-the-shelf topic models trained on large-scale industrial corpora, including Latent Dirichlet Allocation (LDA), SentenceLDA and Topical Word Embedding (TWE). We further describe typical applications which are successfully powered by topic modeling, in order to ease the confusions and difficulties of software engineers during topic model selection and utilization.
Tasks	Model Selection, Topic Models
Published	2017-07-31
URL	http://arxiv.org/abs/1707.09823v1
PDF	http://arxiv.org/pdf/1707.09823v1.pdf
PWC	https://paperswithcode.com/paper/familia-an-open-source-toolkit-for-industrial
Repo	https://github.com/Ridew/Familia
Framework	none

NegBio: a high-performance tool for negation and uncertainty detection in radiology reports


Title	NegBio: a high-performance tool for negation and uncertainty detection in radiology reports
Authors	Yifan Peng, Xiaosong Wang, Le Lu, Mohammadhadi Bagheri, Ronald Summers, Zhiyong Lu
Abstract	Negative and uncertain medical findings are frequent in radiology reports, but discriminating them from positive findings remains challenging for information extraction. Here, we propose a new algorithm, NegBio, to detect negative and uncertain findings in radiology reports. Unlike previous rule-based methods, NegBio utilizes patterns on universal dependencies to identify the scope of triggers that are indicative of negation or uncertainty. We evaluated NegBio on four datasets, including two public benchmarking corpora of radiology reports, a new radiology corpus that we annotated for this work, and a public corpus of general clinical texts. Evaluation on these datasets demonstrates that NegBio is highly accurate for detecting negative and uncertain findings and compares favorably to a widely-used state-of-the-art system NegEx (an average of 9.5% improvement in precision and 5.1% in F1-score).
Tasks
Published	2017-12-16
URL	http://arxiv.org/abs/1712.05898v2
PDF	http://arxiv.org/pdf/1712.05898v2.pdf
PWC	https://paperswithcode.com/paper/negbio-a-high-performance-tool-for-negation
Repo	https://github.com/ncbi-nlp/NegBio
Framework	none

Crowdsourcing for Beyond Polarity Sentiment Analysis A Pure Emotion Lexicon


Title	Crowdsourcing for Beyond Polarity Sentiment Analysis A Pure Emotion Lexicon
Authors	Giannis Haralabopoulos, Elena Simperl
Abstract	Sentiment analysis aims to uncover emotions conveyed through information. In its simplest form, it is performed on a polarity basis, where the goal is to classify information with positive or negative emotion. Recent research has explored more nuanced ways to capture emotions that go beyond polarity. For these methods to work, they require a critical resource: a lexicon that is appropriate for the task at hand, in terms of the range of emotions it captures diversity. In the past, sentiment analysis lexicons have been created by experts, such as linguists and behavioural scientists, with strict rules. Lexicon evaluation was also performed by experts or gold standards. In our paper, we propose a crowdsourcing method for lexicon acquisition, which is scalable, cost-effective, and doesn’t require experts or gold standards. We also compare crowd and expert evaluations of the lexicon, to assess the overall lexicon quality, and the evaluation capabilities of the crowd.
Tasks	Sentiment Analysis
Published	2017-10-04
URL	http://arxiv.org/abs/1710.04203v1
PDF	http://arxiv.org/pdf/1710.04203v1.pdf
PWC	https://paperswithcode.com/paper/crowdsourcing-for-beyond-polarity-sentiment
Repo	https://github.com/GiannisH/Lexicon
Framework	none

Scattertext: a Browser-Based Tool for Visualizing how Corpora Differ


Title	Scattertext: a Browser-Based Tool for Visualizing how Corpora Differ
Authors	Jason S. Kessler
Abstract	Scattertext is an open source tool for visualizing linguistic variation between document categories in a language-independent way. The tool presents a scatterplot, where each axis corresponds to the rank-frequency a term occurs in a category of documents. Through a tie-breaking strategy, the tool is able to display thousands of visible term-representing points and find space to legibly label hundreds of them. Scattertext also lends itself to a query-based visualization of how the use of terms with similar embeddings differs between document categories, as well as a visualization for comparing the importance scores of bag-of-words features to univariate metrics.
Tasks
Published	2017-03-02
URL	http://arxiv.org/abs/1703.00565v3
PDF	http://arxiv.org/pdf/1703.00565v3.pdf
PWC	https://paperswithcode.com/paper/scattertext-a-browser-based-tool-for-1
Repo	https://github.com/JasonKessler/scattertext
Framework	tf

Language Identification Using Deep Convolutional Recurrent Neural Networks


Title	Language Identification Using Deep Convolutional Recurrent Neural Networks
Authors	Christian Bartz, Tom Herold, Haojin Yang, Christoph Meinel
Abstract	Language Identification (LID) systems are used to classify the spoken language from a given audio sample and are typically the first step for many spoken language processing tasks, such as Automatic Speech Recognition (ASR) systems. Without automatic language detection, speech utterances cannot be parsed correctly and grammar rules cannot be applied, causing subsequent speech recognition steps to fail. We propose a LID system that solves the problem in the image domain, rather than the audio domain. We use a hybrid Convolutional Recurrent Neural Network (CRNN) that operates on spectrogram images of the provided audio snippets. In extensive experiments we show, that our model is applicable to a range of noisy scenarios and can easily be extended to previously unknown languages, while maintaining its classification accuracy. We release our code and a large scale training set for LID systems to the community.
Tasks	Language Identification, Speech Recognition
Published	2017-08-16
URL	http://arxiv.org/abs/1708.04811v1
PDF	http://arxiv.org/pdf/1708.04811v1.pdf
PWC	https://paperswithcode.com/paper/language-identification-using-deep
Repo	https://github.com/HPI-DeepLearning/crnn-lid
Framework	tf

AffordanceNet: An End-to-End Deep Learning Approach for Object Affordance Detection


Title	AffordanceNet: An End-to-End Deep Learning Approach for Object Affordance Detection
Authors	Thanh-Toan Do, Anh Nguyen, Ian Reid
Abstract	We propose AffordanceNet, a new deep learning approach to simultaneously detect multiple objects and their affordances from RGB images. Our AffordanceNet has two branches: an object detection branch to localize and classify the object, and an affordance detection branch to assign each pixel in the object to its most probable affordance label. The proposed framework employs three key components for effectively handling the multiclass problem in the affordance mask: a sequence of deconvolutional layers, a robust resizing strategy, and a multi-task loss function. The experimental results on the public datasets show that our AffordanceNet outperforms recent state-of-the-art methods by a fair margin, while its end-to-end architecture allows the inference at the speed of 150ms per image. This makes our AffordanceNet well suitable for real-time robotic applications. Furthermore, we demonstrate the effectiveness of AffordanceNet in different testing environments and in real robotic applications. The source code is available at https://github.com/nqanh/affordance-net
Tasks	Object Detection
Published	2017-09-21
URL	http://arxiv.org/abs/1709.07326v3
PDF	http://arxiv.org/pdf/1709.07326v3.pdf
PWC	https://paperswithcode.com/paper/affordancenet-an-end-to-end-deep-learning
Repo	https://github.com/nqanh/affordance-net
Framework	none

Asymmetric Tri-training for Unsupervised Domain Adaptation


Title	Asymmetric Tri-training for Unsupervised Domain Adaptation
Authors	Kuniaki Saito, Yoshitaka Ushiku, Tatsuya Harada
Abstract	Deep-layered models trained on a large number of labeled samples boost the accuracy of many tasks. It is important to apply such models to different domains because collecting many labeled samples in various domains is expensive. In unsupervised domain adaptation, one needs to train a classifier that works well on a target domain when provided with labeled source samples and unlabeled target samples. Although many methods aim to match the distributions of source and target samples, simply matching the distribution cannot ensure accuracy on the target domain. To learn discriminative representations for the target domain, we assume that artificially labeling target samples can result in a good representation. Tri-training leverages three classifiers equally to give pseudo-labels to unlabeled samples, but the method does not assume labeling samples generated from a different domain.In this paper, we propose an asymmetric tri-training method for unsupervised domain adaptation, where we assign pseudo-labels to unlabeled samples and train neural networks as if they are true labels. In our work, we use three networks asymmetrically. By asymmetric, we mean that two networks are used to label unlabeled target samples and one network is trained by the samples to obtain target-discriminative representations. We evaluate our method on digit recognition and sentiment analysis datasets. Our proposed method achieves state-of-the-art performance on the benchmark digit recognition datasets of domain adaptation.
Tasks	Domain Adaptation, Sentiment Analysis, Unsupervised Domain Adaptation
Published	2017-02-27
URL	http://arxiv.org/abs/1702.08400v3
PDF	http://arxiv.org/pdf/1702.08400v3.pdf
PWC	https://paperswithcode.com/paper/asymmetric-tri-training-for-unsupervised
Repo	https://github.com/ksaito-ut/atda
Framework	tf

Nearly Optimal Robust Subspace Tracking


Title	Nearly Optimal Robust Subspace Tracking
Authors	Praneeth Narayanamurthy, Namrata Vaswani
Abstract	In this work, we study the robust subspace tracking (RST) problem and obtain one of the first two provable guarantees for it. The goal of RST is to track sequentially arriving data vectors that lie in a slowly changing low-dimensional subspace, while being robust to corruption by additive sparse outliers. It can also be interpreted as a dynamic (time-varying) extension of robust PCA (RPCA), with the minor difference that RST also requires a short tracking delay. We develop a recursive projected compressive sensing algorithm that we call Nearly Optimal RST via ReProCS (ReProCS-NORST) because its tracking delay is nearly optimal. We prove that NORST solves both the RST and the dynamic RPCA problems under weakened standard RPCA assumptions, two simple extra assumptions (slow subspace change and most outlier magnitudes lower bounded), and a few minor assumptions. Our guarantee shows that NORST enjoys a near optimal tracking delay of $O(r \log n \log(1/\epsilon))$. Its required delay between subspace change times is the same, and its memory complexity is $n$ times this value. Thus both these are also nearly optimal. Here $n$ is the ambient space dimension, $r$ is the subspaces’ dimension, and $\epsilon$ is the tracking accuracy. NORST also has the best outlier tolerance compared with all previous RPCA or RST methods, both theoretically and empirically (including for real videos), without requiring any model on how the outlier support is generated. This is possible because of the extra assumptions it uses.
Tasks	Compressive Sensing
Published	2017-12-17
URL	http://arxiv.org/abs/1712.06061v4
PDF	http://arxiv.org/pdf/1712.06061v4.pdf
PWC	https://paperswithcode.com/paper/nearly-optimal-robust-subspace-tracking
Repo	https://github.com/praneethmurthy/NORST
Framework	none

Exploring the Bounds of the Utility of Context for Object Detection


Title	Exploring the Bounds of the Utility of Context for Object Detection
Authors	Ehud Barnea, Ohad Ben-Shahar
Abstract	The recurring context in which objects appear holds valuable information that can be employed to predict their existence. This intuitive observation indeed led many researchers to endow appearance-based detectors with explicit reasoning about context. The underlying thesis suggests that stronger contextual relations would facilitate greater improvements in detection capacity. In practice, however, the observed improvement in many cases is modest at best, and often only marginal. In this work we seek to improve our understanding of this phenomenon, in part by pursuing an opposite approach. Instead of attempting to improve detection scores by employing context, we treat the utility of context as an optimization problem: to what extent can detection scores be improved by considering context or any other kind of additional information? With this approach we explore the bounds on improvement by using contextual relations between objects and provide a tool for identifying the most helpful ones. We show that simple co-occurrence relations can often provide large gains, while in other cases a significant improvement is simply impossible or impractical with either co-occurrence or more precise spatial relations. To better understand these results we then analyze the ability of context to handle different types of false detections, revealing that tested contextual information cannot ameliorate localization errors, severely limiting its gains. These and additional insights further our understanding on where and why utilization of context for object detection succeeds and fails.
Tasks	Object Detection
Published	2017-11-15
URL	http://arxiv.org/abs/1711.05471v4
PDF	http://arxiv.org/pdf/1711.05471v4.pdf
PWC	https://paperswithcode.com/paper/on-the-utility-of-context-or-the-lack-thereof
Repo	https://github.com/EhudBarnea/ContextAnalysis
Framework	none

Simple And Efficient Architecture Search for Convolutional Neural Networks


Title	Simple And Efficient Architecture Search for Convolutional Neural Networks
Authors	Thomas Elsken, Jan-Hendrik Metzen, Frank Hutter
Abstract	Neural networks have recently had a lot of success for many tasks. However, neural network architectures that perform well are still typically designed manually by experts in a cumbersome trial-and-error process. We propose a new method to automatically search for well-performing CNN architectures based on a simple hill climbing procedure whose operators apply network morphisms, followed by short optimization runs by cosine annealing. Surprisingly, this simple method yields competitive results, despite only requiring resources in the same order of magnitude as training a single network. E.g., on CIFAR-10, our method designs and trains networks with an error rate below 6% in only 12 hours on a single GPU; training for one day reduces this error further, to almost 5%.
Tasks	Neural Architecture Search
Published	2017-11-13
URL	http://arxiv.org/abs/1711.04528v1
PDF	http://arxiv.org/pdf/1711.04528v1.pdf
PWC	https://paperswithcode.com/paper/simple-and-efficient-architecture-search-for
Repo	https://github.com/akwasigroch/NAS_network_morphism
Framework	tf

Adaptive Measurement Network for CS Image Reconstruction


Title	Adaptive Measurement Network for CS Image Reconstruction
Authors	Xuemei Xie, Yuxiang Wang, Guangming Shi, Chenye Wang, Jiang Du, Zhifu Zhao
Abstract	Conventional compressive sensing (CS) reconstruction is very slow for its characteristic of solving an optimization problem. Convolu- tional neural network can realize fast processing while achieving compa- rable results. While CS image recovery with high quality not only de- pends on good reconstruction algorithms, but also good measurements. In this paper, we propose an adaptive measurement network in which measurement is obtained by learning. The new network consists of a fully-connected layer and ReconNet. The fully-connected layer which has low-dimension output acts as measurement. We train the fully-connected layer and ReconNet simultaneously and obtain adaptive measurement. Because the adaptive measurement fits dataset better, in contrast with random Gaussian measurement matrix, under the same measuremen- t rate, it can extract the information of scene more efficiently and get better reconstruction results. Experiments show that the new network outperforms the original one.
Tasks	Compressive Sensing, Image Reconstruction
Published	2017-09-23
URL	http://arxiv.org/abs/1710.01244v1
PDF	http://arxiv.org/pdf/1710.01244v1.pdf
PWC	https://paperswithcode.com/paper/adaptive-measurement-network-for-cs-image
Repo	https://github.com/Chinmayrane16/ReconNet-PyTorch
Framework	pytorch

Learning from Millions of 3D Scans for Large-scale 3D Face Recognition


Title	Learning from Millions of 3D Scans for Large-scale 3D Face Recognition
Authors	Syed Zulqarnain Gilani, Ajmal Mian
Abstract	Deep networks trained on millions of facial images are believed to be closely approaching human-level performance in face recognition. However, open world face recognition still remains a challenge. Although, 3D face recognition has an inherent edge over its 2D counterpart, it has not benefited from the recent developments in deep learning due to the unavailability of large training as well as large test datasets. Recognition accuracies have already saturated on existing 3D face datasets due to their small gallery sizes. Unlike 2D photographs, 3D facial scans cannot be sourced from the web causing a bottleneck in the development of deep 3D face recognition networks and datasets. In this backdrop, we propose a method for generating a large corpus of labeled 3D face identities and their multiple instances for training and a protocol for merging the most challenging existing 3D datasets for testing. We also propose the first deep CNN model designed specifically for 3D face recognition and trained on 3.1 Million 3D facial scans of 100K identities. Our test dataset comprises 1,853 identities with a single 3D scan in the gallery and another 31K scans as probes, which is several orders of magnitude larger than existing ones. Without fine tuning on this dataset, our network already outperforms state of the art face recognition by over 10%. We fine tune our network on the gallery set to perform end-to-end large scale 3D face recognition which further improves accuracy. Finally, we show the efficacy of our method for the open world face recognition problem.
Tasks	Face Recognition
Published	2017-11-16
URL	http://arxiv.org/abs/1711.05942v3
PDF	http://arxiv.org/pdf/1711.05942v3.pdf
PWC	https://paperswithcode.com/paper/learning-from-millions-of-3d-scans-for-large
Repo	https://github.com/huyhieupham/3D-Face-Recognition
Framework	none

H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation from CT Volumes


Title	H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation from CT Volumes
Authors	Xiaomeng Li, Hao Chen, Xiaojuan Qi, Qi Dou, Chi-Wing Fu, Pheng Ann Heng
Abstract	Liver cancer is one of the leading causes of cancer death. To assist doctors in hepatocellular carcinoma diagnosis and treatment planning, an accurate and automatic liver and tumor segmentation method is highly demanded in the clinical practice. Recently, fully convolutional neural networks (FCNs), including 2D and 3D FCNs, serve as the back-bone in many volumetric image segmentation. However, 2D convolutions can not fully leverage the spatial information along the third dimension while 3D convolutions suffer from high computational cost and GPU memory consumption. To address these issues, we propose a novel hybrid densely connected UNet (H-DenseUNet), which consists of a 2D DenseUNet for efficiently extracting intra-slice features and a 3D counterpart for hierarchically aggregating volumetric contexts under the spirit of the auto-context algorithm for liver and tumor segmentation. We formulate the learning process of H-DenseUNet in an end-to-end manner, where the intra-slice representations and inter-slice features can be jointly optimized through a hybrid feature fusion (HFF) layer. We extensively evaluated our method on the dataset of MICCAI 2017 Liver Tumor Segmentation (LiTS) Challenge and 3DIRCADb Dataset. Our method outperformed other state-of-the-arts on the segmentation results of tumors and achieved very competitive performance for liver segmentation even with a single model.
Tasks	Automatic Liver And Tumor Segmentation, Lesion Segmentation, Liver Segmentation, Semantic Segmentation
Published	2017-09-21
URL	http://arxiv.org/abs/1709.07330v3
PDF	http://arxiv.org/pdf/1709.07330v3.pdf
PWC	https://paperswithcode.com/paper/h-denseunet-hybrid-densely-connected-unet-for
Repo	https://github.com/xmengli999/H-DenseUNet
Framework	none

ISTA-Net: Interpretable Optimization-Inspired Deep Network for Image Compressive Sensing


Title	ISTA-Net: Interpretable Optimization-Inspired Deep Network for Image Compressive Sensing
Authors	Jian Zhang, Bernard Ghanem
Abstract	With the aim of developing a fast yet accurate algorithm for compressive sensing (CS) reconstruction of natural images, we combine in this paper the merits of two existing categories of CS methods: the structure insights of traditional optimization-based methods and the speed of recent network-based ones. Specifically, we propose a novel structured deep network, dubbed ISTA-Net, which is inspired by the Iterative Shrinkage-Thresholding Algorithm (ISTA) for optimizing a general $\ell_1$ norm CS reconstruction model. To cast ISTA into deep network form, we develop an effective strategy to solve the proximal mapping associated with the sparsity-inducing regularizer using nonlinear transforms. All the parameters in ISTA-Net (\eg nonlinear transforms, shrinkage thresholds, step sizes, etc.) are learned end-to-end, rather than being hand-crafted. Moreover, considering that the residuals of natural images are more compressible, an enhanced version of ISTA-Net in the residual domain, dubbed {ISTA-Net}$^+$, is derived to further improve CS reconstruction. Extensive CS experiments demonstrate that the proposed ISTA-Nets outperform existing state-of-the-art optimization-based and network-based CS methods by large margins, while maintaining fast computational speed. Our source codes are available: \textsl{http://jianzhang.tech/projects/ISTA-Net}.
Tasks	Compressive Sensing
Published	2017-06-24
URL	http://arxiv.org/abs/1706.07929v2
PDF	http://arxiv.org/pdf/1706.07929v2.pdf
PWC	https://paperswithcode.com/paper/ista-net-interpretable-optimization-inspired
Repo	https://github.com/jianzhangcs/ISTA-Net-PyTorch
Framework	pytorch

Learning to Invert: Signal Recovery via Deep Convolutional Networks


Title	Learning to Invert: Signal Recovery via Deep Convolutional Networks
Authors	Ali Mousavi, Richard G. Baraniuk
Abstract	The promise of compressive sensing (CS) has been offset by two significant challenges. First, real-world data is not exactly sparse in a fixed basis. Second, current high-performance recovery algorithms are slow to converge, which limits CS to either non-real-time applications or scenarios where massive back-end computing is available. In this paper, we attack both of these challenges head-on by developing a new signal recovery framework we call {\em DeepInverse} that learns the inverse transformation from measurement vectors to signals using a {\em deep convolutional network}. When trained on a set of representative images, the network learns both a representation for the signals (addressing challenge one) and an inverse map approximating a greedy or convex recovery algorithm (addressing challenge two). Our experiments indicate that the DeepInverse network closely approximates the solution produced by state-of-the-art CS recovery algorithms yet is hundreds of times faster in run time. The tradeoff for the ultrafast run time is a computationally intensive, off-line training procedure typical to deep networks. However, the training needs to be completed only once, which makes the approach attractive for a host of sparse recovery problems.
Tasks	Compressive Sensing
Published	2017-01-14
URL	http://arxiv.org/abs/1701.03891v1
PDF	http://arxiv.org/pdf/1701.03891v1.pdf
PWC	https://paperswithcode.com/paper/learning-to-invert-signal-recovery-via-deep
Repo	https://github.com/TaihuLight/DeepInverse-Pytorch
Framework	pytorch