July 30, 2019

3051 words 15 mins read

Paper Group AWR 2

Effective Use of Bidirectional Language Modeling for Transfer Learning in Biomedical Named Entity Recognition. Fast and Accurate Image Super Resolution by Deep CNN with Skip Connection and Network in Network. Universal Style Transfer via Feature Transforms. Hashing as Tie-Aware Learning to Rank. Reconstructing Subject-Specific Effect Maps. MIHash: …

Effective Use of Bidirectional Language Modeling for Transfer Learning in Biomedical Named Entity Recognition


Title	Effective Use of Bidirectional Language Modeling for Transfer Learning in Biomedical Named Entity Recognition
Authors	Devendra Singh Sachan, Pengtao Xie, Mrinmaya Sachan, Eric P Xing
Abstract	Biomedical named entity recognition (NER) is a fundamental task in text mining of medical documents and has many applications. Deep learning based approaches to this task have been gaining increasing attention in recent years as their parameters can be learned end-to-end without the need for hand-engineered features. However, these approaches rely on high-quality labeled data, which is expensive to obtain. To address this issue, we investigate how to use unlabeled text data to improve the performance of NER models. Specifically, we train a bidirectional language model (BiLM) on unlabeled data and transfer its weights to “pretrain” an NER model with the same architecture as the BiLM, which results in a better parameter initialization of the NER model. We evaluate our approach on four benchmark datasets for biomedical NER and show that it leads to a substantial improvement in the F1 scores compared with the state-of-the-art approaches. We also show that BiLM weight transfer leads to a faster model training and the pretrained model requires fewer training examples to achieve a particular F1 score.
Tasks	Language Modelling, Named Entity Recognition, Transfer Learning
Published	2017-11-21
URL	http://arxiv.org/abs/1711.07908v3
PDF	http://arxiv.org/pdf/1711.07908v3.pdf
PWC	https://paperswithcode.com/paper/effective-use-of-bidirectional-language
Repo	https://github.com/sreejukomath/NLPProjects
Framework	tf

Fast and Accurate Image Super Resolution by Deep CNN with Skip Connection and Network in Network


Title	Fast and Accurate Image Super Resolution by Deep CNN with Skip Connection and Network in Network
Authors	Jin Yamanaka, Shigesumi Kuwashima, Takio Kurita
Abstract	We propose a highly efficient and faster Single Image Super-Resolution (SISR) model with Deep Convolutional neural networks (Deep CNN). Deep CNN have recently shown that they have a significant reconstruction performance on single-image super-resolution. Current trend is using deeper CNN layers to improve performance. However, deep models demand larger computation resources and is not suitable for network edge devices like mobile, tablet and IoT devices. Our model achieves state of the art reconstruction performance with at least 10 times lower calculation cost by Deep CNN with Residual Net, Skip Connection and Network in Network (DCSCN). A combination of Deep CNNs and Skip connection layers is used as a feature extractor for image features on both local and global area. Parallelized 1x1 CNNs, like the one called Network in Network, is also used for image reconstruction. That structure reduces the dimensions of the previous layer’s output for faster computation with less information loss, and make it possible to process original images directly. Also we optimize the number of layers and filters of each CNN to significantly reduce the calculation cost. Thus, the proposed algorithm not only achieves the state of the art performance but also achieves faster and efficient computation. Code is available at https://github.com/jiny2001/dcscn-super-resolution
Tasks	Image Reconstruction, Image Super-Resolution, Super-Resolution
Published	2017-07-18
URL	http://arxiv.org/abs/1707.05425v6
PDF	http://arxiv.org/pdf/1707.05425v6.pdf
PWC	https://paperswithcode.com/paper/fast-and-accurate-image-super-resolution-by
Repo	https://github.com/dgdelahera/tf-mobile-dcscn
Framework	tf

Universal Style Transfer via Feature Transforms


Title	Universal Style Transfer via Feature Transforms
Authors	Yijun Li, Chen Fang, Jimei Yang, Zhaowen Wang, Xin Lu, Ming-Hsuan Yang
Abstract	Universal style transfer aims to transfer arbitrary visual styles to content images. Existing feed-forward based methods, while enjoying the inference efficiency, are mainly limited by inability of generalizing to unseen styles or compromised visual quality. In this paper, we present a simple yet effective method that tackles these limitations without training on any pre-defined styles. The key ingredient of our method is a pair of feature transforms, whitening and coloring, that are embedded to an image reconstruction network. The whitening and coloring transforms reflect a direct matching of feature covariance of the content image to a given style image, which shares similar spirits with the optimization of Gram matrix based cost in neural style transfer. We demonstrate the effectiveness of our algorithm by generating high-quality stylized images with comparisons to a number of recent methods. We also analyze our method by visualizing the whitened features and synthesizing textures via simple feature coloring.
Tasks	Image Reconstruction, Style Transfer
Published	2017-05-23
URL	http://arxiv.org/abs/1705.08086v2
PDF	http://arxiv.org/pdf/1705.08086v2.pdf
PWC	https://paperswithcode.com/paper/universal-style-transfer-via-feature
Repo	https://github.com/smaranjitghose/DeepHoli
Framework	none

Hashing as Tie-Aware Learning to Rank


Title	Hashing as Tie-Aware Learning to Rank
Authors	Kun He, Fatih Cakir, Sarah Adel Bargal, Stan Sclaroff
Abstract	Hashing, or learning binary embeddings of data, is frequently used in nearest neighbor retrieval. In this paper, we develop learning to rank formulations for hashing, aimed at directly optimizing ranking-based evaluation metrics such as Average Precision (AP) and Normalized Discounted Cumulative Gain (NDCG). We first observe that the integer-valued Hamming distance often leads to tied rankings, and propose to use tie-aware versions of AP and NDCG to evaluate hashing for retrieval. Then, to optimize tie-aware ranking metrics, we derive their continuous relaxations, and perform gradient-based optimization with deep neural networks. Our results establish the new state-of-the-art for image retrieval by Hamming ranking in common benchmarks.
Tasks	Image Retrieval, Learning-To-Rank
Published	2017-05-23
URL	http://arxiv.org/abs/1705.08562v4
PDF	http://arxiv.org/pdf/1705.08562v4.pdf
PWC	https://paperswithcode.com/paper/hashing-as-tie-aware-learning-to-rank
Repo	https://github.com/kunhe/TALR
Framework	none

Reconstructing Subject-Specific Effect Maps


Title	Reconstructing Subject-Specific Effect Maps
Authors	Ender Konukoglu, Ben Glocker
Abstract	Predictive models allow subject-specific inference when analyzing disease related alterations in neuroimaging data. Given a subject’s data, inference can be made at two levels: global, i.e. identifiying condition presence for the subject, and local, i.e. detecting condition effect on each individual measurement extracted from the subject’s data. While global inference is widely used, local inference, which can be used to form subject-specific effect maps, is rarely used because existing models often yield noisy detections composed of dispersed isolated islands. In this article, we propose a reconstruction method, named RSM, to improve subject-specific detections of predictive modeling approaches and in particular, binary classifiers. RSM specifically aims to reduce noise due to sampling error associated with using a finite sample of examples to train classifiers. The proposed method is a wrapper-type algorithm that can be used with different binary classifiers in a diagnostic manner, i.e. without information on condition presence. Reconstruction is posed as a Maximum-A-Posteriori problem with a prior model whose parameters are estimated from training data in a classifier-specific fashion. Experimental evaluation is performed on synthetically generated data and data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database. Results on synthetic data demonstrate that using RSM yields higher detection accuracy compared to using models directly or with bootstrap averaging. Analyses on the ADNI dataset show that RSM can also improve correlation between subject-specific detections in cortical thickness data and non-imaging markers of Alzheimer’s Disease (AD), such as the Mini Mental State Examination Score and Cerebrospinal Fluid amyloid-$\beta$ levels. Further reliability studies on the longitudinal ADNI dataset show improvement on detection reliability when RSM is used.
Tasks
Published	2017-01-10
URL	http://arxiv.org/abs/1701.02610v3
PDF	http://arxiv.org/pdf/1701.02610v3.pdf
PWC	https://paperswithcode.com/paper/reconstructing-subject-specific-effect-maps
Repo	https://github.com/orobix/Visual-Feature-Attribution-Using-Wasserstein-GANs-Pytorch
Framework	pytorch

MIHash: Online Hashing with Mutual Information


Title	MIHash: Online Hashing with Mutual Information
Authors	Fatih Cakir, Kun He, Sarah Adel Bargal, Stan Sclaroff
Abstract	Learning-based hashing methods are widely used for nearest neighbor retrieval, and recently, online hashing methods have demonstrated good performance-complexity trade-offs by learning hash functions from streaming data. In this paper, we first address a key challenge for online hashing: the binary codes for indexed data must be recomputed to keep pace with updates to the hash functions. We propose an efficient quality measure for hash functions, based on an information-theoretic quantity, mutual information, and use it successfully as a criterion to eliminate unnecessary hash table updates. Next, we also show how to optimize the mutual information objective using stochastic gradient descent. We thus develop a novel hashing method, MIHash, that can be used in both online and batch settings. Experiments on image retrieval benchmarks (including a 2.5M image dataset) confirm the effectiveness of our formulation, both in reducing hash table recomputations and in learning high-quality hash functions.
Tasks	Image Retrieval
Published	2017-03-27
URL	http://arxiv.org/abs/1703.08919v2
PDF	http://arxiv.org/pdf/1703.08919v2.pdf
PWC	https://paperswithcode.com/paper/mihash-online-hashing-with-mutual-information
Repo	https://github.com/fcakir/mihash
Framework	none

Predicting Slice-to-Volume Transformation in Presence of Arbitrary Subject Motion


Title	Predicting Slice-to-Volume Transformation in Presence of Arbitrary Subject Motion
Authors	Benjamin Hou, Amir Alansary, Steven McDonagh, Alice Davidson, Mary Rutherford, Jo V. Hajnal, Daniel Rueckert, Ben Glocker, Bernhard Kainz
Abstract	This paper aims to solve a fundamental problem in intensity-based 2D/3D registration, which concerns the limited capture range and need for very good initialization of state-of-the-art image registration methods. We propose a regression approach that learns to predict rotation and translations of arbitrary 2D image slices from 3D volumes, with respect to a learned canonical atlas co-ordinate system. To this end, we utilize Convolutional Neural Networks (CNNs) to learn the highly complex regression function that maps 2D image slices into their correct position and orientation in 3D space. Our approach is attractive in challenging imaging scenarios, where significant subject motion complicates reconstruction performance of 3D volumes from 2D slice data. We extensively evaluate the effectiveness of our approach quantitatively on simulated MRI brain data with extreme random motion. We further demonstrate qualitative results on fetal MRI where our method is integrated into a full reconstruction and motion compensation pipeline. With our CNN regression approach we obtain an average prediction error of 7mm on simulated data, and convincing reconstruction quality of images of very young fetuses where previous methods fail. We further discuss applications to Computed Tomography and X-ray projections. Our approach is a general solution to the 2D/3D initialization problem. It is computationally efficient, with prediction times per slice of a few milliseconds, making it suitable for real-time scenarios.
Tasks	Image Registration, Motion Compensation
Published	2017-02-28
URL	http://arxiv.org/abs/1702.08891v2
PDF	http://arxiv.org/pdf/1702.08891v2.pdf
PWC	https://paperswithcode.com/paper/predicting-slice-to-volume-transformation-in
Repo	https://github.com/farrell236/SVRnet
Framework	tf

Context Aware Query Image Representation for Particular Object Retrieval


Title	Context Aware Query Image Representation for Particular Object Retrieval
Authors	Zakaria Laskar, Juho Kannala
Abstract	The current models of image representation based on Convolutional Neural Networks (CNN) have shown tremendous performance in image retrieval. Such models are inspired by the information flow along the visual pathway in the human visual cortex. We propose that in the field of particular object retrieval, the process of extracting CNN representations from query images with a given region of interest (ROI) can also be modelled by taking inspiration from human vision. Particularly, we show that by making the CNN pay attention on the ROI while extracting query image representation leads to significant improvement over the baseline methods on challenging Oxford5k and Paris6k datasets. Furthermore, we propose an extension to a recently introduced encoding method for CNN representations, regional maximum activations of convolutions (R-MAC). The proposed extension weights the regional representations using a novel saliency measure prior to aggregation. This leads to further improvement in retrieval accuracy.
Tasks	Image Retrieval
Published	2017-03-03
URL	http://arxiv.org/abs/1703.01226v1
PDF	http://arxiv.org/pdf/1703.01226v1.pdf
PWC	https://paperswithcode.com/paper/context-aware-query-image-representation-for
Repo	https://github.com/AaltoVision/Object-Retrieval
Framework	caffe2

Classifying Unordered Feature Sets with Convolutional Deep Averaging Networks


Title	Classifying Unordered Feature Sets with Convolutional Deep Averaging Networks
Authors	Andrew Gardner, Jinko Kanno, Christian A. Duncan, Rastko R. Selmic
Abstract	Unordered feature sets are a nonstandard data structure that traditional neural networks are incapable of addressing in a principled manner. Providing a concatenation of features in an arbitrary order may lead to the learning of spurious patterns or biases that do not actually exist. Another complication is introduced if the number of features varies between each set. We propose convolutional deep averaging networks (CDANs) for classifying and learning representations of datasets whose instances comprise variable-size, unordered feature sets. CDANs are efficient, permutation-invariant, and capable of accepting sets of arbitrary size. We emphasize the importance of nonlinear feature embeddings for obtaining effective CDAN classifiers and illustrate their advantages in experiments versus linear embeddings and alternative permutation-invariant and -equivariant architectures.
Tasks
Published	2017-09-10
URL	http://arxiv.org/abs/1709.03019v1
PDF	http://arxiv.org/pdf/1709.03019v1.pdf
PWC	https://paperswithcode.com/paper/classifying-unordered-feature-sets-with
Repo	https://github.com/a-gardner1/CDANs
Framework	tf

BB_twtr at SemEval-2017 Task 4: Twitter Sentiment Analysis with CNNs and LSTMs


Title	BB_twtr at SemEval-2017 Task 4: Twitter Sentiment Analysis with CNNs and LSTMs
Authors	Mathieu Cliche
Abstract	In this paper we describe our attempt at producing a state-of-the-art Twitter sentiment classifier using Convolutional Neural Networks (CNNs) and Long Short Term Memory (LSTMs) networks. Our system leverages a large amount of unlabeled data to pre-train word embeddings. We then use a subset of the unlabeled data to fine tune the embeddings using distant supervision. The final CNNs and LSTMs are trained on the SemEval-2017 Twitter dataset where the embeddings are fined tuned again. To boost performances we ensemble several CNNs and LSTMs together. Our approach achieved first rank on all of the five English subtasks amongst 40 teams.
Tasks	Sentiment Analysis, Twitter Sentiment Analysis, Word Embeddings
Published	2017-04-20
URL	http://arxiv.org/abs/1704.06125v1
PDF	http://arxiv.org/pdf/1704.06125v1.pdf
PWC	https://paperswithcode.com/paper/bb_twtr-at-semeval-2017-task-4-twitter
Repo	https://github.com/saurabhrathor/InceptionModel_SentimentAnalysis
Framework	none

The importance of stain normalization in colorectal tissue classification with convolutional networks


Title	The importance of stain normalization in colorectal tissue classification with convolutional networks
Authors	Francesco Ciompi, Oscar Geessink, Babak Ehteshami Bejnordi, Gabriel Silva de Souza, Alexi Baidoshvili, Geert Litjens, Bram van Ginneken, Iris Nagtegaal, Jeroen van der Laak
Abstract	The development of reliable imaging biomarkers for the analysis of colorectal cancer (CRC) in hematoxylin and eosin (H&E) stained histopathology images requires an accurate and reproducible classification of the main tissue components in the image. In this paper, we propose a system for CRC tissue classification based on convolutional networks (ConvNets). We investigate the importance of stain normalization in tissue classification of CRC tissue samples in H&E-stained images. Furthermore, we report the performance of ConvNets on a cohort of rectal cancer samples and on an independent publicly available dataset of colorectal H&E images.
Tasks
Published	2017-02-20
URL	http://arxiv.org/abs/1702.05931v2
PDF	http://arxiv.org/pdf/1702.05931v2.pdf
PWC	https://paperswithcode.com/paper/the-importance-of-stain-normalization-in
Repo	https://github.com/francescociompi/stain-normalization-isbi-2017
Framework	none

Learning Feature Pyramids for Human Pose Estimation


Title	Learning Feature Pyramids for Human Pose Estimation
Authors	Wei Yang, Shuang Li, Wanli Ouyang, Hongsheng Li, Xiaogang Wang
Abstract	Articulated human pose estimation is a fundamental yet challenging task in computer vision. The difficulty is particularly pronounced in scale variations of human body parts when camera view changes or severe foreshortening happens. Although pyramid methods are widely used to handle scale changes at inference time, learning feature pyramids in deep convolutional neural networks (DCNNs) is still not well explored. In this work, we design a Pyramid Residual Module (PRMs) to enhance the invariance in scales of DCNNs. Given input features, the PRMs learn convolutional filters on various scales of input features, which are obtained with different subsampling ratios in a multi-branch network. Moreover, we observe that it is inappropriate to adopt existing methods to initialize the weights of multi-branch networks, which achieve superior performance than plain networks in many tasks recently. Therefore, we provide theoretic derivation to extend the current weight initialization scheme to multi-branch network structures. We investigate our method on two standard benchmarks for human pose estimation. Our approach obtains state-of-the-art results on both benchmarks. Code is available at https://github.com/bearpaw/PyraNet.
Tasks	Pose Estimation
Published	2017-08-03
URL	http://arxiv.org/abs/1708.01101v1
PDF	http://arxiv.org/pdf/1708.01101v1.pdf
PWC	https://paperswithcode.com/paper/learning-feature-pyramids-for-human-pose
Repo	https://github.com/IcewineChen/pytorch-PyraNet
Framework	pytorch

A Unified View of Piecewise Linear Neural Network Verification


Title	A Unified View of Piecewise Linear Neural Network Verification
Authors	Rudy Bunel, Ilker Turkaslan, Philip H. S. Torr, Pushmeet Kohli, M. Pawan Kumar
Abstract	The success of Deep Learning and its potential use in many safety-critical applications has motivated research on formal verification of Neural Network (NN) models. Despite the reputation of learned NN models to behave as black boxes and the theoretical hardness of proving their properties, researchers have been successful in verifying some classes of models by exploiting their piecewise linear structure and taking insights from formal methods such as Satisifiability Modulo Theory. These methods are however still far from scaling to realistic neural networks. To facilitate progress on this crucial area, we make two key contributions. First, we present a unified framework that encompasses previous methods. This analysis results in the identification of new methods that combine the strengths of multiple existing approaches, accomplishing a speedup of two orders of magnitude compared to the previous state of the art. Second, we propose a new data set of benchmarks which includes a collection of previously released testcases. We use the benchmark to provide the first experimental comparison of existing algorithms and identify the factors impacting the hardness of verification problems.
Tasks
Published	2017-11-01
URL	http://arxiv.org/abs/1711.00455v3
PDF	http://arxiv.org/pdf/1711.00455v3.pdf
PWC	https://paperswithcode.com/paper/a-unified-view-of-piecewise-linear-neural
Repo	https://github.com/kaixiao/PLNN
Framework	pytorch

The HASYv2 dataset


Title	The HASYv2 dataset
Authors	Martin Thoma
Abstract	This paper describes the HASYv2 dataset. HASY is a publicly available, free of charge dataset of single symbols similar to MNIST. It contains 168233 instances of 369 classes. HASY contains two challenges: A classification challenge with 10 pre-defined folds for 10-fold cross-validation and a verification challenge.
Tasks
Published	2017-01-29
URL	http://arxiv.org/abs/1701.08380v1
PDF	http://arxiv.org/pdf/1701.08380v1.pdf
PWC	https://paperswithcode.com/paper/the-hasyv2-dataset
Repo	https://github.com/schmollgruberja/Machine-Learning-Nanodegree
Framework	none

A framework for Multi-A(rmed)/B(andit) testing with online FDR control


Title	A framework for Multi-A(rmed)/B(andit) testing with online FDR control
Authors	Fanny Yang, Aaditya Ramdas, Kevin Jamieson, Martin J. Wainwright
Abstract	We propose an alternative framework to existing setups for controlling false alarms when multiple A/B tests are run over time. This setup arises in many practical applications, e.g. when pharmaceutical companies test new treatment options against control pills for different diseases, or when internet companies test their default webpages versus various alternatives over time. Our framework proposes to replace a sequence of A/B tests by a sequence of best-arm MAB instances, which can be continuously monitored by the data scientist. When interleaving the MAB tests with an an online false discovery rate (FDR) algorithm, we can obtain the best of both worlds: low sample complexity and any time online FDR control. Our main contributions are: (i) to propose reasonable definitions of a null hypothesis for MAB instances; (ii) to demonstrate how one can derive an always-valid sequential p-value that allows continuous monitoring of each MAB test; and (iii) to show that using rejection thresholds of online-FDR algorithms as the confidence levels for the MAB algorithms results in both sample-optimality, high power and low FDR at any point in time. We run extensive simulations to verify our claims, and also report results on real data collected from the New Yorker Cartoon Caption contest.
Tasks
Published	2017-06-16
URL	http://arxiv.org/abs/1706.05378v2
PDF	http://arxiv.org/pdf/1706.05378v2.pdf
PWC	https://paperswithcode.com/paper/a-framework-for-multi-armedbandit-testing
Repo	https://github.com/fanny-yang/MABFDR
Framework	none