May 7, 2019

2926 words 14 mins read

Paper Group AWR 31

Using Distributed Representations to Disambiguate Biomedical and Clinical Concepts. Aspect Level Sentiment Classification with Deep Memory Network. Growing Graphs with Hyperedge Replacement Graph Grammars. InterpoNet, A brain inspired neural network for optical flow dense interpolation. Implementing a Reverse Dictionary, based on word definitions, …

Using Distributed Representations to Disambiguate Biomedical and Clinical Concepts


Title	Using Distributed Representations to Disambiguate Biomedical and Clinical Concepts
Authors	Stéphan Tulkens, Simon Šuster, Walter Daelemans
Abstract	In this paper, we report a knowledge-based method for Word Sense Disambiguation in the domains of biomedical and clinical text. We combine word representations created on large corpora with a small number of definitions from the UMLS to create concept representations, which we then compare to representations of the context of ambiguous terms. Using no relational information, we obtain comparable performance to previous approaches on the MSH-WSD dataset, which is a well-known dataset in the biomedical domain. Additionally, our method is fast and easy to set up and extend to other domains. Supplementary materials, including source code, can be found at https: //github.com/clips/yarn
Tasks	Word Sense Disambiguation
Published	2016-08-19
URL	http://arxiv.org/abs/1608.05605v1
PDF	http://arxiv.org/pdf/1608.05605v1.pdf
PWC	https://paperswithcode.com/paper/using-distributed-representations-to
Repo	https://github.com/clips/yarn
Framework	none

Aspect Level Sentiment Classification with Deep Memory Network


Title	Aspect Level Sentiment Classification with Deep Memory Network
Authors	Duyu Tang, Bing Qin, Ting Liu
Abstract	We introduce a deep memory network for aspect level sentiment classification. Unlike feature-based SVM and sequential neural models such as LSTM, this approach explicitly captures the importance of each context word when inferring the sentiment polarity of an aspect. Such importance degree and text representation are calculated with multiple computational layers, each of which is a neural attention model over an external memory. Experiments on laptop and restaurant datasets demonstrate that our approach performs comparable to state-of-art feature based SVM system, and substantially better than LSTM and attention-based LSTM architectures. On both datasets we show that multiple computational layers could improve the performance. Moreover, our approach is also fast. The deep memory network with 9 layers is 15 times faster than LSTM with a CPU implementation.
Tasks	Aspect-Based Sentiment Analysis
Published	2016-05-28
URL	http://arxiv.org/abs/1605.08900v2
PDF	http://arxiv.org/pdf/1605.08900v2.pdf
PWC	https://paperswithcode.com/paper/aspect-level-sentiment-classification-with-1
Repo	https://github.com/mayurikumari047/Aspect-Based-Sentiment-Analysis-Multiple-Models
Framework	tf

Growing Graphs with Hyperedge Replacement Graph Grammars


Title	Growing Graphs with Hyperedge Replacement Graph Grammars
Authors	Salvador Aguiñaga, Rodrigo Palacios, David Chiang, Tim Weninger
Abstract	Discovering the underlying structures present in large real world graphs is a fundamental scientific problem. In this paper we show that a graph’s clique tree can be used to extract a hyperedge replacement grammar. If we store an ordering from the extraction process, the extracted graph grammar is guaranteed to generate an isomorphic copy of the original graph. Or, a stochastic application of the graph grammar rules can be used to quickly create random graphs. In experiments on large real world networks, we show that random graphs, generated from extracted graph grammars, exhibit a wide range of properties that are very similar to the original graphs. In addition to graph properties like degree or eigenvector centrality, what a graph “looks like” ultimately depends on small details in local graph substructures that are difficult to define at a global level. We show that our generative graph model is able to preserve these local substructures when generating new graphs and performs well on new and difficult tests of model robustness.
Tasks
Published	2016-08-10
URL	http://arxiv.org/abs/1608.03192v1
PDF	http://arxiv.org/pdf/1608.03192v1.pdf
PWC	https://paperswithcode.com/paper/growing-graphs-with-hyperedge-replacement
Repo	https://github.com/nddsg/HRG
Framework	none

InterpoNet, A brain inspired neural network for optical flow dense interpolation


Title	InterpoNet, A brain inspired neural network for optical flow dense interpolation
Authors	Shay Zweig, Lior Wolf
Abstract	Sparse-to-dense interpolation for optical flow is a fundamental phase in the pipeline of most of the leading optical flow estimation algorithms. The current state-of-the-art method for interpolation, EpicFlow, is a local average method based on an edge aware geodesic distance. We propose a new data-driven sparse-to-dense interpolation algorithm based on a fully convolutional network. We draw inspiration from the filling-in process in the visual cortex and introduce lateral dependencies between neurons and multi-layer supervision into our learning process. We also show the importance of the image contour to the learning process. Our method is robust and outperforms EpicFlow on competitive optical flow benchmarks with several underlying matching algorithms. This leads to state-of-the-art performance on the Sintel and KITTI 2012 benchmarks.
Tasks	Optical Flow Estimation
Published	2016-11-29
URL	http://arxiv.org/abs/1611.09803v3
PDF	http://arxiv.org/pdf/1611.09803v3.pdf
PWC	https://paperswithcode.com/paper/interponet-a-brain-inspired-neural-network
Repo	https://github.com/shayzweig/InterpoNet
Framework	tf

Implementing a Reverse Dictionary, based on word definitions, using a Node-Graph Architecture


Title	Implementing a Reverse Dictionary, based on word definitions, using a Node-Graph Architecture
Authors	Sushrut Thorat, Varad Choudhari
Abstract	In this paper, we outline an approach to build graph-based reverse dictionaries using word definitions. A reverse dictionary takes a phrase as an input and outputs a list of words semantically similar to that phrase. It is a solution to the Tip-of-the-Tongue problem. We use a distance-based similarity measure, computed on a graph, to assess the similarity between a word and the input phrase. We compare the performance of our approach with the Onelook Reverse Dictionary and a distributional semantics method based on word2vec, and show that our approach is much better than the distributional semantics method, and as good as Onelook, on a 3k lexicon. This simple approach sets a new performance baseline for reverse dictionaries.
Tasks
Published	2016-05-31
URL	http://arxiv.org/abs/1606.00025v5
PDF	http://arxiv.org/pdf/1606.00025v5.pdf
PWC	https://paperswithcode.com/paper/implementing-a-reverse-dictionary-based-on
Repo	https://github.com/novelmartis/RD16demo
Framework	none

Kernelized Weighted SUSAN based Fuzzy C-Means Clustering for Noisy Image Segmentation


Title	Kernelized Weighted SUSAN based Fuzzy C-Means Clustering for Noisy Image Segmentation
Authors	Satrajit Mukherjee, Bodhisattwa Prasad Majumder, Aritran Piplai, Swagatam Das
Abstract	The paper proposes a novel Kernelized image segmentation scheme for noisy images that utilizes the concept of Smallest Univalue Segment Assimilating Nucleus (SUSAN) and incorporates spatial constraints by computing circular colour map induced weights. Fuzzy damping coefficients are obtained for each nucleus or center pixel on the basis of the corresponding weighted SUSAN area values, the weights being equal to the inverse of the number of horizontal and vertical moves required to reach a neighborhood pixel from the center pixel. These weights are used to vary the contributions of the different nuclei in the Kernel based framework. The paper also presents an edge quality metric obtained by fuzzy decision based edge candidate selection and final computation of the blurriness of the edges after their selection. The inability of existing algorithms to preserve edge information and structural details in their segmented maps necessitates the computation of the edge quality factor (EQF) for all the competing algorithms. Qualitative and quantitative analysis have been rendered with respect to state-of-the-art algorithms and for images ridden with varying types of noises. Speckle noise ridden SAR images and Rician noise ridden Magnetic Resonance Images have also been considered for evaluating the effectiveness of the proposed algorithm in extracting important segmentation information.
Tasks	Semantic Segmentation
Published	2016-03-28
URL	http://arxiv.org/abs/1603.08564v1
PDF	http://arxiv.org/pdf/1603.08564v1.pdf
PWC	https://paperswithcode.com/paper/kernelized-weighted-susan-based-fuzzy-c-means
Repo	https://github.com/majumderb/TheFaultEngine
Framework	none

Inverting face embeddings with convolutional neural networks


Title	Inverting face embeddings with convolutional neural networks
Authors	Andrey Zhmoginov, Mark Sandler
Abstract	Deep neural networks have dramatically advanced the state of the art for many areas of machine learning. Recently they have been shown to have a remarkable ability to generate highly complex visual artifacts such as images and text rather than simply recognize them. In this work we use neural networks to effectively invert low-dimensional face embeddings while producing realistically looking consistent images. Our contribution is twofold, first we show that a gradient ascent style approaches can be used to reproduce consistent images, with a help of a guiding image. Second, we demonstrate that we can train a separate neural network to effectively solve the minimization problem in one pass, and generate images in real-time. We then evaluate the loss imposed by using a neural network instead of the gradient descent by comparing the final values of the minimized loss function.
Tasks	Face Transfer
Published	2016-06-14
URL	http://arxiv.org/abs/1606.04189v2
PDF	http://arxiv.org/pdf/1606.04189v2.pdf
PWC	https://paperswithcode.com/paper/inverting-face-embeddings-with-convolutional
Repo	https://github.com/pavelgonchar/face-transfer-tensorflow
Framework	tf

Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections


Title	Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections
Authors	Xiao-Jiao Mao, Chunhua Shen, Yu-Bin Yang
Abstract	In this paper, we propose a very deep fully convolutional encoding-decoding framework for image restoration such as denoising and super-resolution. The network is composed of multiple layers of convolution and de-convolution operators, learning end-to-end mappings from corrupted images to the original ones. The convolutional layers act as the feature extractor, which capture the abstraction of image contents while eliminating noises/corruptions. De-convolutional layers are then used to recover the image details. We propose to symmetrically link convolutional and de-convolutional layers with skip-layer connections, with which the training converges much faster and attains a higher-quality local optimum. First, The skip connections allow the signal to be back-propagated to bottom layers directly, and thus tackles the problem of gradient vanishing, making training deep networks easier and achieving restoration performance gains consequently. Second, these skip connections pass image details from convolutional layers to de-convolutional layers, which is beneficial in recovering the original image. Significantly, with the large capacity, we can handle different levels of noises using a single model. Experimental results show that our network achieves better performance than all previously reported state-of-the-art methods.
Tasks	Denoising, Image Restoration, Image Super-Resolution, Super-Resolution
Published	2016-03-30
URL	http://arxiv.org/abs/1603.09056v2
PDF	http://arxiv.org/pdf/1603.09056v2.pdf
PWC	https://paperswithcode.com/paper/image-restoration-using-very-deep
Repo	https://github.com/ifnspaml/Enhancement-Coded-Speech
Framework	tf

Yum-me: A Personalized Nutrient-based Meal Recommender System


Title	Yum-me: A Personalized Nutrient-based Meal Recommender System
Authors	Longqi Yang, Cheng-Kang Hsieh, Hongjian Yang, Nicola Dell, Serge Belongie, Curtis Cole, Deborah Estrin
Abstract	Nutrient-based meal recommendations have the potential to help individuals prevent or manage conditions such as diabetes and obesity. However, learning people’s food preferences and making recommendations that simultaneously appeal to their palate and satisfy nutritional expectations are challenging. Existing approaches either only learn high-level preferences or require a prolonged learning period. We propose Yum-me, a personalized nutrient-based meal recommender system designed to meet individuals’ nutritional expectations, dietary restrictions, and fine-grained food preferences. Yum-me enables a simple and accurate food preference profiling procedure via a visual quiz-based user interface, and projects the learned profile into the domain of nutritionally appropriate food options to find ones that will appeal to the user. We present the design and implementation of Yum-me, and further describe and evaluate two innovative contributions. The first contriution is an open source state-of-the-art food image analysis model, named FoodDist. We demonstrate FoodDist’s superior performance through careful benchmarking and discuss its applicability across a wide array of dietary applications. The second contribution is a novel online learning framework that learns food preference from item-wise and pairwise image comparisons. We evaluate the framework in a field study of 227 anonymous users and demonstrate that it outperforms other baselines by a significant margin. We further conducted an end-to-end validation of the feasibility and effectiveness of Yum-me through a 60-person user study, in which Yum-me improves the recommendation acceptance rate by 42.63%.
Tasks	Recommendation Systems
Published	2016-05-25
URL	http://arxiv.org/abs/1605.07722v3
PDF	http://arxiv.org/pdf/1605.07722v3.pdf
PWC	https://paperswithcode.com/paper/yum-me-a-personalized-nutrient-based-meal
Repo	https://github.com/ylongqi/FoodDist
Framework	none

Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising


Title	Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
Authors	Kai Zhang, Wangmeng Zuo, Yunjin Chen, Deyu Meng, Lei Zhang
Abstract	Discriminative model learning for image denoising has been recently attracting considerable attentions due to its favorable denoising performance. In this paper, we take one step forward by investigating the construction of feed-forward denoising convolutional neural networks (DnCNNs) to embrace the progress in very deep architecture, learning algorithm, and regularization method into image denoising. Specifically, residual learning and batch normalization are utilized to speed up the training process as well as boost the denoising performance. Different from the existing discriminative denoising models which usually train a specific model for additive white Gaussian noise (AWGN) at a certain noise level, our DnCNN model is able to handle Gaussian denoising with unknown noise level (i.e., blind Gaussian denoising). With the residual learning strategy, DnCNN implicitly removes the latent clean image in the hidden layers. This property motivates us to train a single DnCNN model to tackle with several general image denoising tasks such as Gaussian denoising, single image super-resolution and JPEG image deblocking. Our extensive experiments demonstrate that our DnCNN model can not only exhibit high effectiveness in several general image denoising tasks, but also be efficiently implemented by benefiting from GPU computing.
Tasks	Denoising, Image Denoising, Image Super-Resolution, Super-Resolution
Published	2016-08-13
URL	http://arxiv.org/abs/1608.03981v1
PDF	http://arxiv.org/pdf/1608.03981v1.pdf
PWC	https://paperswithcode.com/paper/beyond-a-gaussian-denoiser-residual-learning
Repo	https://github.com/shibuiwilliam/DeepLearningDenoise
Framework	none

Multi-Objective Deep Reinforcement Learning


Title	Multi-Objective Deep Reinforcement Learning
Authors	Hossam Mossalam, Yannis M. Assael, Diederik M. Roijers, Shimon Whiteson
Abstract	We propose Deep Optimistic Linear Support Learning (DOL) to solve high-dimensional multi-objective decision problems where the relative importances of the objectives are not known a priori. Using features from the high-dimensional inputs, DOL computes the convex coverage set containing all potential optimal solutions of the convex combinations of the objectives. To our knowledge, this is the first time that deep reinforcement learning has succeeded in learning multi-objective policies. In addition, we provide a testbed with two experiments to be used as a benchmark for deep multi-objective reinforcement learning.
Tasks
Published	2016-10-09
URL	http://arxiv.org/abs/1610.02707v1
PDF	http://arxiv.org/pdf/1610.02707v1.pdf
PWC	https://paperswithcode.com/paper/multi-objective-deep-reinforcement-learning
Repo	https://github.com/hossam-mossalam/multi-objective-deep-rl
Framework	none

Tricks from Deep Learning


Title	Tricks from Deep Learning
Authors	Atılım Güneş Baydin, Barak A. Pearlmutter, Jeffrey Mark Siskind
Abstract	The deep learning community has devised a diverse set of methods to make gradient optimization, using large datasets, of large and highly complex models with deeply cascaded nonlinearities, practical. Taken as a whole, these methods constitute a breakthrough, allowing computational structures which are quite wide, very deep, and with an enormous number and variety of free parameters to be effectively optimized. The result now dominates much of practical machine learning, with applications in machine translation, computer vision, and speech recognition. Many of these methods, viewed through the lens of algorithmic differentiation (AD), can be seen as either addressing issues with the gradient itself, or finding ways of achieving increased efficiency using tricks that are AD-related, but not provided by current AD systems. The goal of this paper is to explain not just those methods of most relevance to AD, but also the technical constraints and mindset which led to their discovery. After explaining this context, we present a “laundry list” of methods developed by the deep learning community. Two of these are discussed in further mathematical detail: a way to dramatically reduce the size of the tape when performing reverse-mode AD on a (theoretically) time-reversible process like an ODE integrator; and a new mathematical insight that allows for the implementation of a stochastic Newton’s method.
Tasks	Machine Translation, Speech Recognition
Published	2016-11-10
URL	http://arxiv.org/abs/1611.03777v1
PDF	http://arxiv.org/pdf/1611.03777v1.pdf
PWC	https://paperswithcode.com/paper/tricks-from-deep-learning
Repo	https://github.com/nirmalsinghania2008/Tricks-for-Deep-Learning
Framework	none

Video2GIF: Automatic Generation of Animated GIFs from Video


Title	Video2GIF: Automatic Generation of Animated GIFs from Video
Authors	Michael Gygli, Yale Song, Liangliang Cao
Abstract	We introduce the novel problem of automatically generating animated GIFs from video. GIFs are short looping video with no sound, and a perfect combination between image and video that really capture our attention. GIFs tell a story, express emotion, turn events into humorous moments, and are the new wave of photojournalism. We pose the question: Can we automate the entirely manual and elaborate process of GIF creation by leveraging the plethora of user generated GIF content? We propose a Robust Deep RankNet that, given a video, generates a ranked list of its segments according to their suitability as GIF. We train our model to learn what visual content is often selected for GIFs by using over 100K user generated GIFs and their corresponding video sources. We effectively deal with the noisy web data by proposing a novel adaptive Huber loss in the ranking formulation. We show that our approach is robust to outliers and picks up several patterns that are frequently present in popular animated GIFs. On our new large-scale benchmark dataset, we show the advantage of our approach over several state-of-the-art methods.
Tasks
Published	2016-05-16
URL	http://arxiv.org/abs/1605.04850v1
PDF	http://arxiv.org/pdf/1605.04850v1.pdf
PWC	https://paperswithcode.com/paper/video2gif-automatic-generation-of-animated
Repo	https://github.com/gifs/personalized-highlights-dataset
Framework	none

GPflow: A Gaussian process library using TensorFlow


Title	GPflow: A Gaussian process library using TensorFlow
Authors	Alexander G. de G. Matthews, Mark van der Wilk, Tom Nickson, Keisuke Fujii, Alexis Boukouvalas, Pablo León-Villagrá, Zoubin Ghahramani, James Hensman
Abstract	GPflow is a Gaussian process library that uses TensorFlow for its core computations and Python for its front end. The distinguishing features of GPflow are that it uses variational inference as the primary approximation method, provides concise code through the use of automatic differentiation, has been engineered with a particular emphasis on software testing and is able to exploit GPU hardware.
Tasks
Published	2016-10-27
URL	http://arxiv.org/abs/1610.08733v1
PDF	http://arxiv.org/pdf/1610.08733v1.pdf
PWC	https://paperswithcode.com/paper/gpflow-a-gaussian-process-library-using
Repo	https://github.com/markvdw/GPflow-inter-domain
Framework	tf

Embedded real-time stereo estimation via Semi-Global Matching on the GPU


Title	Embedded real-time stereo estimation via Semi-Global Matching on the GPU
Authors	Daniel Hernandez-Juarez, Alejandro Chacón, Antonio Espinosa, David Vázquez, Juan Carlos Moure, Antonio Manuel López
Abstract	Dense, robust and real-time computation of depth information from stereo-camera systems is a computationally demanding requirement for robotics, advanced driver assistance systems (ADAS) and autonomous vehicles. Semi-Global Matching (SGM) is a widely used algorithm that propagates consistency constraints along several paths across the image. This work presents a real-time system producing reliable disparity estimation results on the new embedded energy-efficient GPU devices. Our design runs on a Tegra X1 at 42 frames per second (fps) for an image size of 640x480, 128 disparity levels, and using 4 path directions for the SGM method.
Tasks	Autonomous Vehicles, Disparity Estimation
Published	2016-10-13
URL	http://arxiv.org/abs/1610.04121v1
PDF	http://arxiv.org/pdf/1610.04121v1.pdf
PWC	https://paperswithcode.com/paper/embedded-real-time-stereo-estimation-via-semi
Repo	https://github.com/dhernandez0/sgm
Framework	none