October 21, 2019

2740 words 13 mins read

Paper Group AWR 87

Paper Group AWR 87

Blind Image Deconvolution using Deep Generative Priors. Iterative Residual Image Deconvolution. Fourier-Domain Optimization for Image Processing. Enriching Knowledge Bases with Counting Quantifiers. Visual Explanations From Deep 3D Convolutional Neural Networks for Alzheimer’s Disease Classification. Learning to Explain: An Information-Theoretic Pe …

Blind Image Deconvolution using Deep Generative Priors

Title Blind Image Deconvolution using Deep Generative Priors
Authors Muhammad Asim, Fahad Shamshad, Ali Ahmed
Abstract This paper proposes a novel approach to regularize the \textit{ill-posed} and \textit{non-linear} blind image deconvolution (blind deblurring) using deep generative networks as priors. We employ two separate generative models — one trained to produce sharp images while the other trained to generate blur kernels from lower-dimensional parameters. To deblur, we propose an alternating gradient descent scheme operating in the latent lower-dimensional space of each of the pretrained generative models. Our experiments show promising deblurring results on images even under large blurs, and heavy noise. To address the shortcomings of generative models such as mode collapse, we augment our generative priors with classical image priors and report improved performance on complex image datasets. The deblurring performance depends on how well the range of the generator spans the image class. Interestingly, our experiments show that even an untrained structured (convolutional) generative networks acts as an image prior in the image deblurring context allowing us to extend our results to more diverse natural image datasets.
Tasks Deblurring, Image Deconvolution
Published 2018-02-12
URL http://arxiv.org/abs/1802.04073v4
PDF http://arxiv.org/pdf/1802.04073v4.pdf
PWC https://paperswithcode.com/paper/blind-image-deconvolution-using-deep
Repo https://github.com/axium/Blind-Image-Deconvolution-using-Deep-Generative-Priors
Framework tf

Iterative Residual Image Deconvolution

Title Iterative Residual Image Deconvolution
Authors Li Si-Yao, Dongwei Ren, Furong Zhao, Zijian Hu, Junfeng Li, Qian Yin
Abstract Image deblurring, a.k.a. image deconvolution, recovers a clear image from pixel superposition caused by blur degradation. Few deep convolutional neural networks (CNN) succeed in addressing this task. In this paper, we first demonstrate that the minimum-mean-square-error (MMSE) solution to image deblurring can be interestingly unfolded into a series of residual components. Based on this analysis, we propose a novel iterative residual deconvolution (IRD) algorithm. Further, IRD motivates us to take one step forward to design an explicable and effective CNN architecture for image deconvolution. Specifically, a sequence of residual CNN units are deployed, whose intermediate outputs are then concatenated and integrated, resulting in concatenated residual convolutional network (CRCNet). The experimental results demonstrate that proposed CRCNet not only achieves better quantitative metrics but also recovers more visually plausible texture details compared with state-of-the-art methods.
Tasks Deblurring, Image Deconvolution
Published 2018-04-17
URL http://arxiv.org/abs/1804.06042v2
PDF http://arxiv.org/pdf/1804.06042v2.pdf
PWC https://paperswithcode.com/paper/iterative-residual-image-deconvolution
Repo https://github.com/lisiyaoATbnu/crcnet
Framework pytorch

Fourier-Domain Optimization for Image Processing

Title Fourier-Domain Optimization for Image Processing
Authors Majed El Helou, Frederike Dümbgen, Radhakrishna Achanta, Sabine Süsstrunk
Abstract Image optimization problems encompass many applications such as spectral fusion, deblurring, deconvolution, dehazing, matting, reflection removal and image interpolation, among others. With current image sizes in the order of megabytes, it is extremely expensive to run conventional algorithms such as gradient descent, making them unfavorable especially when closed-form solutions can be derived and computed efficiently. This paper explains in detail the framework for solving convex image optimization and deconvolution in the Fourier domain. We begin by explaining the mathematical background and motivating why the presented setups can be transformed and solved very efficiently in the Fourier domain. We also show how to practically use these solutions, by providing the corresponding implementations. The explanations are aimed at a broad audience with minimal knowledge of convolution and image optimization. The eager reader can jump to Section 3 for a footprint of how to solve and implement a sample optimization function, and Section 5 for the more complex cases.
Tasks Deblurring
Published 2018-09-11
URL http://arxiv.org/abs/1809.04187v1
PDF http://arxiv.org/pdf/1809.04187v1.pdf
PWC https://paperswithcode.com/paper/fourier-domain-optimization-for-image
Repo https://github.com/duembgen/fourier-deconv
Framework none

Enriching Knowledge Bases with Counting Quantifiers

Title Enriching Knowledge Bases with Counting Quantifiers
Authors Paramita Mirza, Simon Razniewski, Fariz Darari, Gerhard Weikum
Abstract Information extraction traditionally focuses on extracting relations between identifiable entities, such as <Monterey, locatedIn, California>. Yet, texts often also contain Counting information, stating that a subject is in a specific relation with a number of objects, without mentioning the objects themselves, for example, “California is divided into 58 counties”. Such counting quantifiers can help in a variety of tasks such as query answering or knowledge base curation, but are neglected by prior work. This paper develops the first full-fledged system for extracting counting information from text, called CINEX. We employ distant supervision using fact counts from a knowledge base as training seeds, and develop novel techniques for dealing with several challenges: (i) non-maximal training seeds due to the incompleteness of knowledge bases, (ii) sparse and skewed observations in text sources, and (iii) high diversity of linguistic patterns. Experiments with five human-evaluated relations show that CINEX can achieve 60% average precision for extracting counting information. In a large-scale experiment, we demonstrate the potential for knowledge base enrichment by applying CINEX to 2,474 frequent relations in Wikidata. CINEX can assert the existence of 2.5M facts for 110 distinct relations, which is 28% more than the existing Wikidata facts for these relations.
Tasks
Published 2018-07-10
URL http://arxiv.org/abs/1807.03656v1
PDF http://arxiv.org/pdf/1807.03656v1.pdf
PWC https://paperswithcode.com/paper/enriching-knowledge-bases-with-counting
Repo https://github.com/paramitamirza/CINEX
Framework none

Visual Explanations From Deep 3D Convolutional Neural Networks for Alzheimer’s Disease Classification

Title Visual Explanations From Deep 3D Convolutional Neural Networks for Alzheimer’s Disease Classification
Authors Chengliang Yang, Anand Rangarajan, Sanjay Ranka
Abstract We develop three efficient approaches for generating visual explanations from 3D convolutional neural networks (3D-CNNs) for Alzheimer’s disease classification. One approach conducts sensitivity analysis on hierarchical 3D image segmentation, and the other two visualize network activations on a spatial map. Visual checks and a quantitative localization benchmark indicate that all approaches identify important brain parts for Alzheimer’s disease diagnosis. Comparative analysis show that the sensitivity analysis based approach has difficulty handling loosely distributed cerebral cortex, and approaches based on visualization of activations are constrained by the resolution of the convolutional layer. The complementarity of these methods improves the understanding of 3D-CNNs in Alzheimer’s disease classification from different perspectives.
Tasks Semantic Segmentation
Published 2018-03-07
URL http://arxiv.org/abs/1803.02544v3
PDF http://arxiv.org/pdf/1803.02544v3.pdf
PWC https://paperswithcode.com/paper/visual-explanations-from-deep-3d
Repo https://github.com/west-gates/3DCNN-Vis
Framework none

Learning to Explain: An Information-Theoretic Perspective on Model Interpretation

Title Learning to Explain: An Information-Theoretic Perspective on Model Interpretation
Authors Jianbo Chen, Le Song, Martin J. Wainwright, Michael I. Jordan
Abstract We introduce instancewise feature selection as a methodology for model interpretation. Our method is based on learning a function to extract a subset of features that are most informative for each given example. This feature selector is trained to maximize the mutual information between selected features and the response variable, where the conditional distribution of the response variable given the input is the model to be explained. We develop an efficient variational approximation to the mutual information, and show the effectiveness of our method on a variety of synthetic and real data sets using both quantitative metrics and human evaluation.
Tasks Feature Selection
Published 2018-02-21
URL http://arxiv.org/abs/1802.07814v2
PDF http://arxiv.org/pdf/1802.07814v2.pdf
PWC https://paperswithcode.com/paper/learning-to-explain-an-information-theoretic
Repo https://github.com/Jianbo-Lab/L2X
Framework tf

Measuring Semantic Coherence of a Conversation

Title Measuring Semantic Coherence of a Conversation
Authors Svitlana Vakulenko, Maarten de Rijke, Michael Cochez, Vadim Savenkov, Axel Polleres
Abstract Conversational systems have become increasingly popular as a way for humans to interact with computers. To be able to provide intelligent responses, conversational systems must correctly model the structure and semantics of a conversation. We introduce the task of measuring semantic (in)coherence in a conversation with respect to background knowledge, which relies on the identification of semantic relations between concepts introduced during a conversation. We propose and evaluate graph-based and machine learning-based approaches for measuring semantic coherence using knowledge graphs, their vector space embeddings and word embedding models, as sources of background knowledge. We demonstrate how these approaches are able to uncover different coherence patterns in conversations on the Ubuntu Dialogue Corpus.
Tasks Knowledge Graphs
Published 2018-06-17
URL http://arxiv.org/abs/1806.06411v1
PDF http://arxiv.org/pdf/1806.06411v1.pdf
PWC https://paperswithcode.com/paper/measuring-semantic-coherence-of-a
Repo https://github.com/svakulenk0/semantic_coherence
Framework none

Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey

Title Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey
Authors Naveed Akhtar, Ajmal Mian
Abstract Deep learning is at the heart of the current rise of machine learning and artificial intelligence. In the field of Computer Vision, it has become the workhorse for applications ranging from self-driving cars to surveillance and security. Whereas deep neural networks have demonstrated phenomenal success (often beyond human capabilities) in solving complex problems, recent studies show that they are vulnerable to adversarial attacks in the form of subtle perturbations to inputs that lead a model to predict incorrect outputs. For images, such perturbations are often too small to be perceptible, yet they completely fool the deep learning models. Adversarial attacks pose a serious threat to the success of deep learning in practice. This fact has lead to a large influx of contributions in this direction. This article presents the first comprehensive survey on adversarial attacks on deep learning in Computer Vision. We review the works that design adversarial attacks, analyze the existence of such attacks and propose defenses against them. To emphasize that adversarial attacks are possible in practical conditions, we separately review the contributions that evaluate adversarial attacks in the real-world scenarios. Finally, we draw on the literature to provide a broader outlook of the research direction.
Tasks Self-Driving Cars
Published 2018-01-02
URL http://arxiv.org/abs/1801.00553v3
PDF http://arxiv.org/pdf/1801.00553v3.pdf
PWC https://paperswithcode.com/paper/threat-of-adversarial-attacks-on-deep
Repo https://github.com/saumya0303/attack_image
Framework tf

DeepEmo: Learning and Enriching Pattern-Based Emotion Representations

Title DeepEmo: Learning and Enriching Pattern-Based Emotion Representations
Authors Elvis Saravia, Hsien-Chi Toby Liu, Yi-Shin Chen
Abstract We propose a graph-based mechanism to extract rich-emotion bearing patterns, which fosters a deeper analysis of online emotional expressions, from a corpus. The patterns are then enriched with word embeddings and evaluated through several emotion recognition tasks. Moreover, we conduct analysis on the emotion-oriented patterns to demonstrate its applicability and to explore its properties. Our experimental results demonstrate that the proposed techniques outperform most state-of-the-art emotion recognition techniques.
Tasks Emotion Recognition, Word Embeddings
Published 2018-04-24
URL http://arxiv.org/abs/1804.08847v1
PDF http://arxiv.org/pdf/1804.08847v1.pdf
PWC https://paperswithcode.com/paper/deepemo-learning-and-enriching-pattern-based
Repo https://github.com/omarsar/twitter_crawler_by_keywords
Framework none

HybridSVD: When Collaborative Information is Not Enough

Title HybridSVD: When Collaborative Information is Not Enough
Authors Evgeny Frolov, Ivan Oseledets
Abstract We propose a new hybrid algorithm that allows incorporating both user and item side information within the standard collaborative filtering technique. One of its key features is that it naturally extends a simple PureSVD approach and inherits its unique advantages, such as highly efficient Lanczos-based optimization procedure, simplified hyper-parameter tuning and a quick folding-in computation for generating recommendations instantly even in highly dynamic online environments. The algorithm utilizes a generalized formulation of the singular value decomposition, which adds flexibility to the solution and allows imposing the desired structure on its latent space. Conveniently, the resulting model also admits an efficient and straightforward solution for the cold start scenario. We evaluate our approach on a diverse set of datasets and show its superiority over similar classes of hybrid models.
Tasks Model Selection
Published 2018-02-18
URL https://arxiv.org/abs/1802.06398v4
PDF https://arxiv.org/pdf/1802.06398v4.pdf
PWC https://paperswithcode.com/paper/hybridsvd-when-collaborative-information-is
Repo https://github.com/evfro/kdd2018
Framework none

Constraint-based Causal Discovery for Non-Linear Structural Causal Models with Cycles and Latent Confounders

Title Constraint-based Causal Discovery for Non-Linear Structural Causal Models with Cycles and Latent Confounders
Authors Patrick Forré, Joris M. Mooij
Abstract We address the problem of causal discovery from data, making use of the recently proposed causal modeling framework of modular structural causal models (mSCM) to handle cycles, latent confounders and non-linearities. We introduce {\sigma}-connection graphs ({\sigma}-CG), a new class of mixed graphs (containing undirected, bidirected and directed edges) with additional structure, and extend the concept of {\sigma}-separation, the appropriate generalization of the well-known notion of d-separation in this setting, to apply to {\sigma}-CGs. We prove the closedness of {\sigma}-separation under marginalisation and conditioning and exploit this to implement a test of {\sigma}-separation on a {\sigma}-CG. This then leads us to the first causal discovery algorithm that can handle non-linear functional relations, latent confounders, cyclic causal relationships, and data from different (stochastic) perfect interventions. As a proof of concept, we show on synthetic data how well the algorithm recovers features of the causal graph of modular structural causal models.
Tasks Causal Discovery
Published 2018-07-09
URL http://arxiv.org/abs/1807.03024v1
PDF http://arxiv.org/pdf/1807.03024v1.pdf
PWC https://paperswithcode.com/paper/constraint-based-causal-discovery-for-non
Repo https://github.com/caus-am/sigmasep
Framework none

Multiclass Weighted Loss for Instance Segmentation of Cluttered Cells

Title Multiclass Weighted Loss for Instance Segmentation of Cluttered Cells
Authors Fidel A. Guerrero-Pena, Pedro D. Marrero Fernandez, Tsang Ing Ren, Mary Yui, Ellen Rothenberg, Alexandre Cunha
Abstract We propose a new multiclass weighted loss function for instance segmentation of cluttered cells. We are primarily motivated by the need of developmental biologists to quantify and model the behavior of blood T-cells which might help us in understanding their regulation mechanisms and ultimately help researchers in their quest for developing an effective immuno-therapy cancer treatment. Segmenting individual touching cells in cluttered regions is challenging as the feature distribution on shared borders and cell foreground are similar thus difficulting discriminating pixels into proper classes. We present two novel weight maps applied to the weighted cross entropy loss function which take into account both class imbalance and cell geometry. Binary ground truth training data is augmented so the learning model can handle not only foreground and background but also a third touching class. This framework allows training using U-Net. Experiments with our formulations have shown superior results when compared to other similar schemes, outperforming binary class models with significant improvement of boundary adequacy and instance detection. We validate our results on manually annotated microscope images of T-cells.
Tasks Instance Segmentation, Semantic Segmentation
Published 2018-02-21
URL http://arxiv.org/abs/1802.07465v1
PDF http://arxiv.org/pdf/1802.07465v1.pdf
PWC https://paperswithcode.com/paper/multiclass-weighted-loss-for-instance
Repo https://github.com/juglab/VoidSeg
Framework tf

code2seq: Generating Sequences from Structured Representations of Code

Title code2seq: Generating Sequences from Structured Representations of Code
Authors Uri Alon, Shaked Brody, Omer Levy, Eran Yahav
Abstract The ability to generate natural language sequences from source code snippets has a variety of applications such as code summarization, documentation, and retrieval. Sequence-to-sequence (seq2seq) models, adopted from neural machine translation (NMT), have achieved state-of-the-art performance on these tasks by treating source code as a sequence of tokens. We present ${\rm {\scriptsize CODE2SEQ}}$: an alternative approach that leverages the syntactic structure of programming languages to better encode source code. Our model represents a code snippet as the set of compositional paths in its abstract syntax tree (AST) and uses attention to select the relevant paths while decoding. We demonstrate the effectiveness of our approach for two tasks, two programming languages, and four datasets of up to $16$M examples. Our model significantly outperforms previous models that were specifically designed for programming languages, as well as state-of-the-art NMT models. An interactive online demo of our model is available at http://code2seq.org. Our code, data and trained models are available at http://github.com/tech-srl/code2seq.
Tasks Code Summarization
Published 2018-08-04
URL http://arxiv.org/abs/1808.01400v6
PDF http://arxiv.org/pdf/1808.01400v6.pdf
PWC https://paperswithcode.com/paper/code2seq-generating-sequences-from-structured
Repo https://github.com/Attn-to-FC/Attn-to-FC
Framework tf

Streamlining Variational Inference for Constraint Satisfaction Problems

Title Streamlining Variational Inference for Constraint Satisfaction Problems
Authors Aditya Grover, Tudor Achim, Stefano Ermon
Abstract Several algorithms for solving constraint satisfaction problems are based on survey propagation, a variational inference scheme used to obtain approximate marginal probability estimates for variable assignments. These marginals correspond to how frequently each variable is set to true among satisfying assignments, and are used to inform branching decisions during search; however, marginal estimates obtained via survey propagation are approximate and can be self-contradictory. We introduce a more general branching strategy based on streamlining constraints, which sidestep hard assignments to variables. We show that streamlined solvers consistently outperform decimation-based solvers on random k-SAT instances for several problem sizes, shrinking the gap between empirical performance and theoretical limits of satisfiability by 16.3% on average for k=3,4,5,6.
Tasks
Published 2018-11-24
URL http://arxiv.org/abs/1811.09813v1
PDF http://arxiv.org/pdf/1811.09813v1.pdf
PWC https://paperswithcode.com/paper/streamlining-variational-inference-for
Repo https://github.com/ermongroup/streamline-vi-csp
Framework none

Political Popularity Analysis in Social Media

Title Political Popularity Analysis in Social Media
Authors Amir Karami, Aida Elkouri
Abstract Popularity is a critical success factor for a politician and her/his party to win in elections and implement their plans. Finding the reasons behind the popularity can provide a stable political movement. This research attempts to measure popularity in Twitter using a mixed method. In recent years, Twitter data has provided an excellent opportunity for exploring public opinions by analyzing a large number of tweets. This study has collected and examined 4.5 million tweets related to a US politician, Senator Bernie Sanders. This study investigated eight economic reasons behind the senator’s popularity in Twitter. This research has benefits for politicians, informatics experts, and policymakers to explore public opinion. The collected data will also be available for further investigation.
Tasks
Published 2018-12-08
URL http://arxiv.org/abs/1812.03258v1
PDF http://arxiv.org/pdf/1812.03258v1.pdf
PWC https://paperswithcode.com/paper/political-popularity-analysis-in-social-media
Repo https://github.com/amir-karami/Sanders-Tweets-Data
Framework none
comments powered by Disqus