October 21, 2019

3272 words 16 mins read

Paper Group AWR 137

MRI Tumor Segmentation with Densely Connected 3D CNN. A new robust feature selection method using variance-based sensitivity analysis. Fact Checking in Community Forums. DropBlock: A regularization method for convolutional networks. A Study into the similarity in generator and discriminator in GAN architecture. Multilevel Wavelet Decomposition Netw …

MRI Tumor Segmentation with Densely Connected 3D CNN


Title	MRI Tumor Segmentation with Densely Connected 3D CNN
Authors	Lele Chen, Yue Wu, Adora M. DSouza, Anas Z. Abidin, Axel Wismuller, Chenliang Xu
Abstract	Glioma is one of the most common and aggressive types of primary brain tumors. The accurate segmentation of subcortical brain structures is crucial to the study of gliomas in that it helps the monitoring of the progression of gliomas and aids the evaluation of treatment outcomes. However, the large amount of required human labor makes it difficult to obtain the manually segmented Magnetic Resonance Imaging (MRI) data, limiting the use of precise quantitative measurements in the clinical practice. In this work, we try to address this problem by developing a 3D Convolutional Neural Network~(3D CNN) based model to automatically segment gliomas. The major difficulty of our segmentation model comes with the fact that the location, structure, and shape of gliomas vary significantly among different patients. In order to accurately classify each voxel, our model captures multi-scale contextual information by extracting features from two scales of receptive fields. To fully exploit the tumor structure, we propose a novel architecture that hierarchically segments different lesion regions of the necrotic and non-enhancing tumor~(NCR/NET), peritumoral edema~(ED) and GD-enhancing tumor~(ET). Additionally, we utilize densely connected convolutional blocks to further boost the performance. We train our model with a patch-wise training schema to mitigate the class imbalance problem. The proposed method is validated on the BraTS 2017 dataset and it achieves Dice scores of 0.72, 0.83 and 0.81 for the complete tumor, tumor core and enhancing tumor, respectively. These results are comparable to the reported state-of-the-art results, and our method is better than existing 3D-based methods in terms of compactness, time and space efficiency.
Tasks
Published	2018-01-18
URL	http://arxiv.org/abs/1802.02427v2
PDF	http://arxiv.org/pdf/1802.02427v2.pdf
PWC	https://paperswithcode.com/paper/mri-tumor-segmentation-with-densely-connected
Repo	https://github.com/lelechen63/MRI-tumor-segmentation-Brats
Framework	tf

A new robust feature selection method using variance-based sensitivity analysis


Title	A new robust feature selection method using variance-based sensitivity analysis
Authors	Saman Sadeghyan
Abstract	Excluding irrelevant features in a pattern recognition task plays an important role in maintaining a simpler machine learning model and optimizing the computational efficiency. Nowadays with the rise of large scale datasets, feature selection is in great demand as it becomes a central issue when facing high-dimensional datasets. The present study provides a new measure of saliency for features by employing a Sensitivity Analysis (SA) technique called the extended Fourier amplitude sensitivity test, and a well-trained Feedforward Neural Network (FNN) model, which ultimately leads to the selection of a promising optimal feature subset. Ideas of the paper are mainly demonstrated based on adopting FNN model for feature selection in classification problems. But in the end, a generalization framework is discussed in order to give insights into the usage in regression problems as well as expressing how other function approximate models can be deployed. Effectiveness of the proposed method is verified by result analysis and data visualization for a series of experiments over several well-known datasets drawn from UCI machine learning repository.
Tasks	Feature Selection
Published	2018-04-13
URL	http://arxiv.org/abs/1804.05092v1
PDF	http://arxiv.org/pdf/1804.05092v1.pdf
PWC	https://paperswithcode.com/paper/a-new-robust-feature-selection-method-using
Repo	https://github.com/5amron/feature_selection_using_sensitivity_analysis
Framework	none

Fact Checking in Community Forums


Title	Fact Checking in Community Forums
Authors	Tsvetomila Mihaylova, Preslav Nakov, Lluis Marquez, Alberto Barron-Cedeno, Mitra Mohtarami, Georgi Karadzhov, James Glass
Abstract	Community Question Answering (cQA) forums are very popular nowadays, as they represent effective means for communities around particular topics to share information. Unfortunately, this information is not always factual. Thus, here we explore a new dimension in the context of cQA, which has been ignored so far: checking the veracity of answers to particular questions in cQA forums. As this is a new problem, we create a specialized dataset for it. We further propose a novel multi-faceted model, which captures information from the answer content (what is said and how), from the author profile (who says it), from the rest of the community forum (where it is said), and from external authoritative sources of information (external support). Evaluation results show a MAP value of 86.54, which is 21 points absolute above the baseline.
Tasks	Community Question Answering, Question Answering
Published	2018-03-08
URL	http://arxiv.org/abs/1803.03178v1
PDF	http://arxiv.org/pdf/1803.03178v1.pdf
PWC	https://paperswithcode.com/paper/fact-checking-in-community-forums
Repo	https://github.com/olabknbit/FactChecking
Framework	none

DropBlock: A regularization method for convolutional networks


Title	DropBlock: A regularization method for convolutional networks
Authors	Golnaz Ghiasi, Tsung-Yi Lin, Quoc V. Le
Abstract	Deep neural networks often work well when they are over-parameterized and trained with a massive amount of noise and regularization, such as weight decay and dropout. Although dropout is widely used as a regularization technique for fully connected layers, it is often less effective for convolutional layers. This lack of success of dropout for convolutional layers is perhaps due to the fact that activation units in convolutional layers are spatially correlated so information can still flow through convolutional networks despite dropout. Thus a structured form of dropout is needed to regularize convolutional networks. In this paper, we introduce DropBlock, a form of structured dropout, where units in a contiguous region of a feature map are dropped together. We found that applying DropbBlock in skip connections in addition to the convolution layers increases the accuracy. Also, gradually increasing number of dropped units during training leads to better accuracy and more robust to hyperparameter choices. Extensive experiments show that DropBlock works better than dropout in regularizing convolutional networks. On ImageNet classification, ResNet-50 architecture with DropBlock achieves $78.13%$ accuracy, which is more than $1.6%$ improvement on the baseline. On COCO detection, DropBlock improves Average Precision of RetinaNet from $36.8%$ to $38.4%$.
Tasks
Published	2018-10-30
URL	http://arxiv.org/abs/1810.12890v1
PDF	http://arxiv.org/pdf/1810.12890v1.pdf
PWC	https://paperswithcode.com/paper/dropblock-a-regularization-method-for
Repo	https://github.com/gan3sh500/dropblock
Framework	pytorch

A Study into the similarity in generator and discriminator in GAN architecture


Title	A Study into the similarity in generator and discriminator in GAN architecture
Authors	Arjun Karuvally
Abstract	One popular generative model that has high-quality results is the Generative Adversarial Networks(GAN). This type of architecture consists of two separate networks that play against each other. The generator creates an output from the input noise that is given to it. The discriminator has the task of determining if the input to it is real or fake. This takes place constantly eventually leads to the generator modeling the target distribution. This paper includes a study into the actual weights learned by the network and a study into the similarity of the discriminator and generator networks. The paper also tries to leverage the similarity between these networks and shows that indeed both the networks may have a similar structure with experimental evidence with a novel shared architecture.
Tasks
Published	2018-02-21
URL	http://arxiv.org/abs/1802.07401v1
PDF	http://arxiv.org/pdf/1802.07401v1.pdf
PWC	https://paperswithcode.com/paper/a-study-into-the-similarity-in-generator-and
Repo	https://github.com/arjun23496/Shared-WGAN
Framework	tf

Multilevel Wavelet Decomposition Network for Interpretable Time Series Analysis


Title	Multilevel Wavelet Decomposition Network for Interpretable Time Series Analysis
Authors	Jingyuan Wang, Ze Wang, Jianfeng Li, Junjie Wu
Abstract	Recent years have witnessed the unprecedented rising of time series from almost all kindes of academic and industrial fields. Various types of deep neural network models have been introduced to time series analysis, but the important frequency information is yet lack of effective modeling. In light of this, in this paper we propose a wavelet-based neural network structure called multilevel Wavelet Decomposition Network (mWDN) for building frequency-aware deep learning models for time series analysis. mWDN preserves the advantage of multilevel discrete wavelet decomposition in frequency learning while enables the fine-tuning of all parameters under a deep neural network framework. Based on mWDN, we further propose two deep learning models called Residual Classification Flow (RCF) and multi-frequecy Long Short-Term Memory (mLSTM) for time series classification and forecasting, respectively. The two models take all or partial mWDN decomposed sub-series in different frequencies as input, and resort to the back propagation algorithm to learn all the parameters globally, which enables seamless embedding of wavelet-based frequency analysis into deep learning frameworks. Extensive experiments on 40 UCR datasets and a real-world user volume dataset demonstrate the excellent performance of our time series models based on mWDN. In particular, we propose an importance analysis method to mWDN based models, which successfully identifies those time-series elements and mWDN layers that are crucially important to time series analysis. This indeed indicates the interpretability advantage of mWDN, and can be viewed as an indepth exploration to interpretable deep learning.
Tasks	Time Series, Time Series Analysis, Time Series Classification
Published	2018-06-23
URL	http://arxiv.org/abs/1806.08946v1
PDF	http://arxiv.org/pdf/1806.08946v1.pdf
PWC	https://paperswithcode.com/paper/multilevel-wavelet-decomposition-network-for
Repo	https://github.com/AHoke/Multilevel_Wavelet_Decomposition_Network_Pytorch
Framework	pytorch

DeepZip: Lossless Data Compression using Recurrent Neural Networks


Title	DeepZip: Lossless Data Compression using Recurrent Neural Networks
Authors	Mohit Goyal, Kedar Tatwawadi, Shubham Chandak, Idoia Ochoa
Abstract	Sequential data is being generated at an unprecedented pace in various forms, including text and genomic data. This creates the need for efficient compression mechanisms to enable better storage, transmission and processing of such data. To solve this problem, many of the existing compressors attempt to learn models for the data and perform prediction-based compression. Since neural networks are known as universal function approximators with the capability to learn arbitrarily complex mappings, and in practice show excellent performance in prediction tasks, we explore and devise methods to compress sequential data using neural network predictors. We combine recurrent neural network predictors with an arithmetic coder and losslessly compress a variety of synthetic, text and genomic datasets. The proposed compressor outperforms Gzip on the real datasets and achieves near-optimal compression for the synthetic datasets. The results also help understand why and where neural networks are good alternatives for traditional finite context models
Tasks
Published	2018-11-20
URL	http://arxiv.org/abs/1811.08162v1
PDF	http://arxiv.org/pdf/1811.08162v1.pdf
PWC	https://paperswithcode.com/paper/deepzip-lossless-data-compression-using
Repo	https://github.com/mohit1997/DeepZip
Framework	tf

TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes


Title	TextSnake: A Flexible Representation for Detecting Text of Arbitrary Shapes
Authors	Shangbang Long, Jiaqiang Ruan, Wenjie Zhang, Xin He, Wenhao Wu, Cong Yao
Abstract	Driven by deep neural networks and large scale datasets, scene text detection methods have progressed substantially over the past years, continuously refreshing the performance records on various standard benchmarks. However, limited by the representations (axis-aligned rectangles, rotated rectangles or quadrangles) adopted to describe text, existing methods may fall short when dealing with much more free-form text instances, such as curved text, which are actually very common in real-world scenarios. To tackle this problem, we propose a more flexible representation for scene text, termed as TextSnake, which is able to effectively represent text instances in horizontal, oriented and curved forms. In TextSnake, a text instance is described as a sequence of ordered, overlapping disks centered at symmetric axes, each of which is associated with potentially variable radius and orientation. Such geometry attributes are estimated via a Fully Convolutional Network (FCN) model. In experiments, the text detector based on TextSnake achieves state-of-the-art or comparable performance on Total-Text and SCUT-CTW1500, the two newly published benchmarks with special emphasis on curved text in natural images, as well as the widely-used datasets ICDAR 2015 and MSRA-TD500. Specifically, TextSnake outperforms the baseline on Total-Text by more than 40% in F-measure.
Tasks	Scene Text Detection
Published	2018-07-04
URL	http://arxiv.org/abs/1807.01544v1
PDF	http://arxiv.org/pdf/1807.01544v1.pdf
PWC	https://paperswithcode.com/paper/textsnake-a-flexible-representation-for
Repo	https://github.com/princewang1994/TextSnake.pytorch
Framework	pytorch

Geoseg: A Computer Vision Package for Automatic Building Segmentation and Outline Extraction


Title	Geoseg: A Computer Vision Package for Automatic Building Segmentation and Outline Extraction
Authors	Guangming Wu, Zhiling Guo
Abstract	Recently, deep learning algorithms, especially fully convolutional network based methods, are becoming very popular in the field of remote sensing. However, these methods are implemented and evaluated through various datasets and deep learning frameworks. There has not been a package that covers these methods in a unifying manner. In this study, we introduce a computer vision package termed Geoseg that focus on building segmentation and outline extraction. Geoseg implements over nine state-of-the-art models as well as utility scripts needed to conduct model training, logging, evaluating and visualization. The implementation of Geoseg emphasizes unification, simplicity, and flexibility. The performance and computational efficiency of all implemented methods are evaluated by comparison experiment through a unified, high-quality aerial image dataset.
Tasks
Published	2018-09-10
URL	http://arxiv.org/abs/1809.03175v1
PDF	http://arxiv.org/pdf/1809.03175v1.pdf
PWC	https://paperswithcode.com/paper/geoseg-a-computer-vision-package-for
Repo	https://github.com/GeoVision-Lab/Geoseg
Framework	none

Object Detection for Comics using Manga109 Annotations


Title	Object Detection for Comics using Manga109 Annotations
Authors	Toru Ogawa, Atsushi Otsubo, Rei Narita, Yusuke Matsui, Toshihiko Yamasaki, Kiyoharu Aizawa
Abstract	With the growth of digitized comics, image understanding techniques are becoming important. In this paper, we focus on object detection, which is a fundamental task of image understanding. Although convolutional neural networks (CNN)-based methods archived good performance in object detection for naturalistic images, there are two problems in applying these methods to the comic object detection task. First, there is no large-scale annotated comics dataset. The CNN-based methods require large-scale annotations for training. Secondly, the objects in comics are highly overlapped compared to naturalistic images. This overlap causes the assignment problem in the existing CNN-based methods. To solve these problems, we proposed a new annotation dataset and a new CNN model. We annotated an existing image dataset of comics and created the largest annotation dataset, named Manga109-annotations. For the assignment problem, we proposed a new CNN-based detector, SSD300-fork. We compared SSD300-fork with other detection methods using Manga109-annotations and confirmed that our model outperformed them based on the mAP score.
Tasks	Object Detection
Published	2018-03-23
URL	http://arxiv.org/abs/1803.08670v2
PDF	http://arxiv.org/pdf/1803.08670v2.pdf
PWC	https://paperswithcode.com/paper/object-detection-for-comics-using-manga109
Repo	https://github.com/matsui528/manga109api
Framework	none

Suspicious News Detection Using Micro Blog Text


Title	Suspicious News Detection Using Micro Blog Text
Authors	Tsubasa Tagami, Hiroki Ouchi, Hiroki Asano, Kazuaki Hanawa, Kaori Uchiyama, Kaito Suzuki, Kentaro Inui, Atsushi Komiya, Atsuo Fujimura, Hitofumi Yanai, Ryo Yamashita, Akinori Machino
Abstract	We present a new task, suspicious news detection using micro blog text. This task aims to support human experts to detect suspicious news articles to be verified, which is costly but a crucial step before verifying the truthfulness of the articles. Specifically, in this task, given a set of posts on SNS referring to a news article, the goal is to judge whether the article is to be verified or not. For this task, we create a publicly available dataset in Japanese and provide benchmark results by using several basic machine learning techniques. Experimental results show that our models can reduce the cost of manual fact-checking process.
Tasks
Published	2018-10-27
URL	http://arxiv.org/abs/1810.11663v1
PDF	http://arxiv.org/pdf/1810.11663v1.pdf
PWC	https://paperswithcode.com/paper/suspicious-news-detection-using-micro-blog
Repo	https://github.com/t-tagami/Suspicious-News-Detection
Framework	none

Fast Feature Extraction with CNNs with Pooling Layers


Title	Fast Feature Extraction with CNNs with Pooling Layers
Authors	Christian Bailer, Tewodros Habtegebrial, Kiran varanasi, Didier Stricker
Abstract	In recent years, many publications showed that convolutional neural network based features can have a superior performance to engineered features. However, not much effort was taken so far to extract local features efficiently for a whole image. In this paper, we present an approach to compute patch-based local feature descriptors efficiently in presence of pooling and striding layers for whole images at once. Our approach is generic and can be applied to nearly all existing network architectures. This includes networks for all local feature extraction tasks like camera calibration, Patchmatching, optical flow estimation and stereo matching. In addition, our approach can be applied to other patch-based approaches like sliding window object detection and recognition. We complete our paper with a speed benchmark of popular CNN based feature extraction approaches applied on a whole image, with and without our speedup, and example code (for Torch) that shows how an arbitrary CNN architecture can be easily converted by our approach.
Tasks	Calibration, Object Detection, Optical Flow Estimation, Stereo Matching
Published	2018-05-08
URL	http://arxiv.org/abs/1805.03096v1
PDF	http://arxiv.org/pdf/1805.03096v1.pdf
PWC	https://paperswithcode.com/paper/fast-feature-extraction-with-cnns-with
Repo	https://github.com/erezposner/Fast_Dense_Feature_Extraction
Framework	tf

StaQC: A Systematically Mined Question-Code Dataset from Stack Overflow


Title	StaQC: A Systematically Mined Question-Code Dataset from Stack Overflow
Authors	Ziyu Yao, Daniel S. Weld, Wei-Peng Chen, Huan Sun
Abstract	Stack Overflow (SO) has been a great source of natural language questions and their code solutions (i.e., question-code pairs), which are critical for many tasks including code retrieval and annotation. In most existing research, question-code pairs were collected heuristically and tend to have low quality. In this paper, we investigate a new problem of systematically mining question-code pairs from Stack Overflow (in contrast to heuristically collecting them). It is formulated as predicting whether or not a code snippet is a standalone solution to a question. We propose a novel Bi-View Hierarchical Neural Network which can capture both the programming content and the textual context of a code snippet (i.e., two views) to make a prediction. On two manually annotated datasets in Python and SQL domain, our framework substantially outperforms heuristic methods with at least 15% higher F1 and accuracy. Furthermore, we present StaQC (Stack Overflow Question-Code pairs), the largest dataset to date of ~148K Python and ~120K SQL question-code pairs, automatically mined from SO using our framework. Under various case studies, we demonstrate that StaQC can greatly help develop data-hungry models for associating natural language with programming language.
Tasks
Published	2018-03-26
URL	http://arxiv.org/abs/1803.09371v1
PDF	http://arxiv.org/pdf/1803.09371v1.pdf
PWC	https://paperswithcode.com/paper/staqc-a-systematically-mined-question-code
Repo	https://github.com/LittleYUYU/StackOverflow-Question-Code-Dataset
Framework	tf

Data-driven Perception of Neuron Point Process with Unknown Unknowns


Title	Data-driven Perception of Neuron Point Process with Unknown Unknowns
Authors	Ruochen Yang, Gaurav Gupta, Paul Bogdan
Abstract	Identification of patterns from discrete data time-series for statistical inference, threat detection, social opinion dynamics, brain activity prediction has received recent momentum. In addition to the huge data size, the associated challenges are, for example, (i) missing data to construct a closed time-varying complex network, and (ii) contribution of unknown sources which are not probed. Towards this end, the current work focuses on statistical neuron system model with multi-covariates and unknown inputs. Previous research of neuron activity analysis is mainly limited with effects from the spiking history of target neuron and the interaction with other neurons in the system while ignoring the influence of unknown stimuli. We propose to use unknown unknowns, which describes the effect of unknown stimuli, undetected neuron activities and all other hidden sources of error. The maximum likelihood estimation with the fixed-point iteration method is implemented. The fixed-point iterations converge fast, and the proposed methods can be efficiently parallelized and offer computational advantage especially when the input spiking trains are over long time-horizon. The developed framework provides an intuition into the meaning of having extra degrees-of-freedom in the data to support the need for unknowns. The proposed algorithm is applied to simulated spike trains and on real-world experimental data of mouse somatosensory, mouse retina and cat retina. The model shows a successful increasing of system likelihood with respect to the conditional intensity function, and it also reveals the convergence with iterations. Results suggest that the neural connection model with unknown unknowns can efficiently estimate the statistical properties of the process by increasing the network likelihood.
Tasks	Activity Prediction, Time Series
Published	2018-11-02
URL	http://arxiv.org/abs/1811.00688v2
PDF	http://arxiv.org/pdf/1811.00688v2.pdf
PWC	https://paperswithcode.com/paper/data-driven-perception-of-neuron-point
Repo	https://github.com/gaurav71531/spikeNetwork
Framework	none

Natural Language Inference over Interaction Space: ICLR 2018 Reproducibility Report


Title	Natural Language Inference over Interaction Space: ICLR 2018 Reproducibility Report
Authors	Martin Mirakyan, Karen Hambardzumyan, Hrant Khachatrian
Abstract	We have tried to reproduce the results of the paper “Natural Language Inference over Interaction Space” submitted to ICLR 2018 conference as part of the ICLR 2018 Reproducibility Challenge. Initially, we were not aware that the code was available, so we started to implement the network from scratch. We have evaluated our version of the model on Stanford NLI dataset and reached 86.38% accuracy on the test set, while the paper claims 88.0% accuracy. The main difference, as we understand it, comes from the optimizers and the way model selection is performed.
Tasks	Model Selection, Natural Language Inference
Published	2018-02-09
URL	http://arxiv.org/abs/1802.03198v1
PDF	http://arxiv.org/pdf/1802.03198v1.pdf
PWC	https://paperswithcode.com/paper/natural-language-inference-over-interaction
Repo	https://github.com/YerevaNN/DIIN-in-Keras
Framework	none