July 26, 2019

3060 words 15 mins read

Paper Group ANR 764

Bayer Demosaicking Using Optimized Mean Curvature over RGB channels. Discriminative Transfer Learning for General Image Restoration. Algebraic Variety Models for High-Rank Matrix Completion. Automatic Liver Lesion Detection using Cascaded Deep Residual Networks. Glass-Box Program Synthesis: A Machine Learning Approach. LoopInvGen: A Loop Invariant …

Bayer Demosaicking Using Optimized Mean Curvature over RGB channels


Title	Bayer Demosaicking Using Optimized Mean Curvature over RGB channels
Authors	Rui Chen, Huizhu Jia, Xiange Wen, Xiaodong Xie
Abstract	Color artifacts of demosaicked images are often found at contours due to interpolation across edges and cross-channel aliasing. To tackle this problem, we propose a novel demosaicking method to reliably reconstruct color channels of a Bayer image based on two different optimized mean-curvature (MC) models. The missing pixel values in green (G) channel are first estimated by minimizing a variational MC model. The curvatures of restored G-image surface are approximated as a linear MC model which guides the initial reconstruction of red (R) and blue (B) channels. Then a refinement process is performed to interpolate accurate full-resolution R and B images. Experiments on benchmark images have testified to the superiority of the proposed method in terms of both the objective and subjective quality.
Tasks	Demosaicking
Published	2017-05-17
URL	http://arxiv.org/abs/1705.06300v1
PDF	http://arxiv.org/pdf/1705.06300v1.pdf
PWC	https://paperswithcode.com/paper/bayer-demosaicking-using-optimized-mean
Repo
Framework

Discriminative Transfer Learning for General Image Restoration


Title	Discriminative Transfer Learning for General Image Restoration
Authors	Lei Xiao, Felix Heide, Wolfgang Heidrich, Bernhard Schölkopf, Michael Hirsch
Abstract	Recently, several discriminative learning approaches have been proposed for effective image restoration, achieving convincing trade-off between image quality and computational efficiency. However, these methods require separate training for each restoration task (e.g., denoising, deblurring, demosaicing) and problem condition (e.g., noise level of input images). This makes it time-consuming and difficult to encompass all tasks and conditions during training. In this paper, we propose a discriminative transfer learning method that incorporates formal proximal optimization and discriminative learning for general image restoration. The method requires a single-pass training and allows for reuse across various problems and conditions while achieving an efficiency comparable to previous discriminative approaches. Furthermore, after being trained, our model can be easily transferred to new likelihood terms to solve untrained tasks, or be combined with existing priors to further improve image restoration quality.
Tasks	Deblurring, Demosaicking, Denoising, Image Restoration, Transfer Learning
Published	2017-03-27
URL	http://arxiv.org/abs/1703.09245v1
PDF	http://arxiv.org/pdf/1703.09245v1.pdf
PWC	https://paperswithcode.com/paper/discriminative-transfer-learning-for-general
Repo
Framework

Algebraic Variety Models for High-Rank Matrix Completion


Title	Algebraic Variety Models for High-Rank Matrix Completion
Authors	Greg Ongie, Rebecca Willett, Robert D. Nowak, Laura Balzano
Abstract	We consider a generalization of low-rank matrix completion to the case where the data belongs to an algebraic variety, i.e. each data point is a solution to a system of polynomial equations. In this case the original matrix is possibly high-rank, but it becomes low-rank after mapping each column to a higher dimensional space of monomial features. Many well-studied extensions of linear models, including affine subspaces and their union, can be described by a variety model. In addition, varieties can be used to model a richer class of nonlinear quadratic and higher degree curves and surfaces. We study the sampling requirements for matrix completion under a variety model with a focus on a union of affine subspaces. We also propose an efficient matrix completion algorithm that minimizes a convex or non-convex surrogate of the rank of the matrix of monomial features. Our algorithm uses the well-known “kernel trick” to avoid working directly with the high-dimensional monomial matrix. We show the proposed algorithm is able to recover synthetically generated data up to the predicted sampling complexity bounds. The proposed algorithm also outperforms standard low rank matrix completion and subspace clustering techniques in experiments with real data.
Tasks	Low-Rank Matrix Completion, Matrix Completion
Published	2017-03-28
URL	http://arxiv.org/abs/1703.09631v1
PDF	http://arxiv.org/pdf/1703.09631v1.pdf
PWC	https://paperswithcode.com/paper/algebraic-variety-models-for-high-rank-matrix
Repo
Framework

Automatic Liver Lesion Detection using Cascaded Deep Residual Networks


Title	Automatic Liver Lesion Detection using Cascaded Deep Residual Networks
Authors	Lei Bi, Jinman Kim, Ashnil Kumar, Dagan Feng
Abstract	Automatic segmentation of liver lesions is a fundamental requirement towards the creation of computer aided diagnosis (CAD) and decision support systems (CDS). Traditional segmentation approaches depend heavily upon hand-crafted features and a priori knowledge of the user. As such, these methods are difficult to adopt within a clinical environment. Recently, deep learning methods based on fully convolutional networks (FCNs) have been successful in many segmentation problems primarily because they leverage a large labelled dataset to hierarchically learn the features that best correspond to the shallow visual appearance as well as the deep semantics of the areas to be segmented. However, FCNs based on a 16 layer VGGNet architecture have limited capacity to add additional layers. Therefore, it is challenging to learn more discriminative features among different classes for FCNs. In this study, we overcome these limitations using deep residual networks (ResNet) to segment liver lesions. ResNet contain skip connections between convolutional layers, which solved the problem of the training degradation of training accuracy in very deep networks and thereby enables the use of additional layers for learning more discriminative features. In addition, we achieve more precise boundary definitions through a novel cascaded ResNet architecture with multi-scale fusion to gradually learn and infer the boundaries of both the liver and the liver lesions. Our proposed method achieved 4th place in the ISBI 2017 Liver Tumor Segmentation Challenge by the submission deadline.
Tasks
Published	2017-04-10
URL	http://arxiv.org/abs/1704.02703v2
PDF	http://arxiv.org/pdf/1704.02703v2.pdf
PWC	https://paperswithcode.com/paper/automatic-liver-lesion-detection-using
Repo
Framework

Glass-Box Program Synthesis: A Machine Learning Approach


Title	Glass-Box Program Synthesis: A Machine Learning Approach
Authors	Konstantina Christakopoulou, Adam Tauman Kalai
Abstract	Recently proposed models which learn to write computer programs from data use either input/output examples or rich execution traces. Instead, we argue that a novel alternative is to use a glass-box loss function, given as a program itself that can be directly inspected. Glass-box optimization covers a wide range of problems, from computing the greatest common divisor of two integers, to learning-to-learn problems. In this paper, we present an intelligent search system which learns, given the partial program and the glass-box problem, the probabilities over the space of programs. We empirically demonstrate that our informed search procedure leads to significant improvements compared to brute-force program search, both in terms of accuracy and time. For our experiments we use rich context free grammars inspired by number theory, text processing, and algebra. Our results show that (i) performing 4 rounds of our framework typically solves about 70% of the target problems, (ii) our framework can improve itself even in domain agnostic scenarios, and (iii) it can solve problems that would be otherwise too slow to solve with brute-force search.
Tasks	Program Synthesis
Published	2017-09-25
URL	http://arxiv.org/abs/1709.08669v1
PDF	http://arxiv.org/pdf/1709.08669v1.pdf
PWC	https://paperswithcode.com/paper/glass-box-program-synthesis-a-machine
Repo
Framework

LoopInvGen: A Loop Invariant Generator based on Precondition Inference


Title	LoopInvGen: A Loop Invariant Generator based on Precondition Inference
Authors	Saswat Padhi, Rahul Sharma, Todd Millstein
Abstract	We describe the LoopInvGen tool for generating loop invariants that can provably guarantee correctness of a program with respect to a given specification. LoopInvGen is an efficient implementation of the inference technique originally proposed in our earlier work on PIE (https://doi.org/10.1145/2908080.2908099). In contrast to existing techniques, LoopInvGen is not restricted to a fixed set of features – atomic predicates that are composed together to build complex loop invariants. Instead, we start with no initial features, and use program synthesis techniques to grow the set on demand. This not only enables a less onerous and more expressive approach, but also appears to be significantly faster than the existing tools over the SyGuS-COMP 2018 benchmarks from the INV track.
Tasks	Program Synthesis
Published	2017-07-07
URL	https://arxiv.org/abs/1707.02029v4
PDF	https://arxiv.org/pdf/1707.02029v4.pdf
PWC	https://paperswithcode.com/paper/loopinvgen-a-loop-invariant-generator-based
Repo
Framework

Analysis and Design of Convolutional Networks via Hierarchical Tensor Decompositions


Title	Analysis and Design of Convolutional Networks via Hierarchical Tensor Decompositions
Authors	Nadav Cohen, Or Sharir, Yoav Levine, Ronen Tamari, David Yakira, Amnon Shashua
Abstract	The driving force behind convolutional networks - the most successful deep learning architecture to date, is their expressive power. Despite its wide acceptance and vast empirical evidence, formal analyses supporting this belief are scarce. The primary notions for formally reasoning about expressiveness are efficiency and inductive bias. Expressive efficiency refers to the ability of a network architecture to realize functions that require an alternative architecture to be much larger. Inductive bias refers to the prioritization of some functions over others given prior knowledge regarding a task at hand. In this paper we overview a series of works written by the authors, that through an equivalence to hierarchical tensor decompositions, analyze the expressive efficiency and inductive bias of various convolutional network architectural features (depth, width, strides and more). The results presented shed light on the demonstrated effectiveness of convolutional networks, and in addition, provide new tools for network design.
Tasks
Published	2017-05-05
URL	http://arxiv.org/abs/1705.02302v5
PDF	http://arxiv.org/pdf/1705.02302v5.pdf
PWC	https://paperswithcode.com/paper/analysis-and-design-of-convolutional-networks
Repo
Framework

Synthesizing Imperative Programs from Examples Guided by Static Analysis


Title	Synthesizing Imperative Programs from Examples Guided by Static Analysis
Authors	Sunbeom So, Hakjoo Oh
Abstract	We present a novel algorithm that synthesizes imperative programs for introductory programming courses. Given a set of input-output examples and a partial program, our algorithm generates a complete program that is consistent with every example. Our key idea is to combine enumerative program synthesis and static analysis, which aggressively prunes out a large search space while guaranteeing to find, if any, a correct solution. We have implemented our algorithm in a tool, called SIMPL, and evaluated it on 30 problems used in introductory programming courses. The results show that SIMPL is able to solve the benchmark problems in 6.6 seconds on average.
Tasks	Program Synthesis
Published	2017-02-21
URL	http://arxiv.org/abs/1702.06334v2
PDF	http://arxiv.org/pdf/1702.06334v2.pdf
PWC	https://paperswithcode.com/paper/synthesizing-imperative-programs-from
Repo
Framework

Densely Connected Convolutional Networks and Signal Quality Analysis to Detect Atrial Fibrillation Using Short Single-Lead ECG Recordings


Title	Densely Connected Convolutional Networks and Signal Quality Analysis to Detect Atrial Fibrillation Using Short Single-Lead ECG Recordings
Authors	Jonathan Rubin, Saman Parvaneh, Asif Rahman, Bryan Conroy, Saeed Babaeizadeh
Abstract	The development of new technology such as wearables that record high-quality single channel ECG, provides an opportunity for ECG screening in a larger population, especially for atrial fibrillation screening. The main goal of this study is to develop an automatic classification algorithm for normal sinus rhythm (NSR), atrial fibrillation (AF), other rhythms (O), and noise from a single channel short ECG segment (9-60 seconds). For this purpose, signal quality index (SQI) along with dense convolutional neural networks was used. Two convolutional neural network (CNN) models (main model that accepts 15 seconds ECG and secondary model that processes 9 seconds shorter ECG) were trained using the training data set. If the recording is determined to be of low quality by SQI, it is immediately classified as noisy. Otherwise, it is transformed to a time-frequency representation and classified with the CNN as NSR, AF, O, or noise. At the final step, a feature-based post-processing algorithm classifies the rhythm as either NSR or O in case the CNN model’s discrimination between the two is indeterminate. The best result achieved at the official phase of the PhysioNet/CinC challenge on the blind test set was 0.80 (F1 for NSR, AF, and O were 0.90, 0.80, and 0.70, respectively).
Tasks
Published	2017-10-10
URL	http://arxiv.org/abs/1710.05817v1
PDF	http://arxiv.org/pdf/1710.05817v1.pdf
PWC	https://paperswithcode.com/paper/densely-connected-convolutional-networks-and
Repo
Framework

Optimal Multi-Object Segmentation with Novel Gradient Vector Flow Based Shape Priors


Title	Optimal Multi-Object Segmentation with Novel Gradient Vector Flow Based Shape Priors
Authors	Junjie Bai, Abhay Shah, Xiaodong Wu
Abstract	Shape priors have been widely utilized in medical image segmentation to improve segmentation accuracy and robustness. A major way to encode such a prior shape model is to use a mesh representation, which is prone to causing self-intersection or mesh folding. Those problems require complex and expensive algorithms to mitigate. In this paper, we propose a novel shape prior directly embedded in the voxel grid space, based on gradient vector flows of a pre-segmentation. The flexible and powerful prior shape representation is ready to be extended to simultaneously segmenting multiple interacting objects with minimum separation distance constraint. The problem is formulated as a Markov random field problem whose exact solution can be efficiently computed with a single minimum s-t cut in an appropriately constructed graph. The proposed algorithm is validated on two multi-object segmentation applications: the brain tissue segmentation in MRI images, and the bladder/prostate segmentation in CT images. Both sets of experiments show superior or competitive performance of the proposed method to other state-of-the-art methods.
Tasks	Medical Image Segmentation, Semantic Segmentation
Published	2017-05-22
URL	http://arxiv.org/abs/1705.10311v1
PDF	http://arxiv.org/pdf/1705.10311v1.pdf
PWC	https://paperswithcode.com/paper/optimal-multi-object-segmentation-with-novel
Repo
Framework

CDC: Convolutional-De-Convolutional Networks for Precise Temporal Action Localization in Untrimmed Videos


Title	CDC: Convolutional-De-Convolutional Networks for Precise Temporal Action Localization in Untrimmed Videos
Authors	Zheng Shou, Jonathan Chan, Alireza Zareian, Kazuyuki Miyazawa, Shih-Fu Chang
Abstract	Temporal action localization is an important yet challenging problem. Given a long, untrimmed video consisting of multiple action instances and complex background contents, we need not only to recognize their action categories, but also to localize the start time and end time of each instance. Many state-of-the-art systems use segment-level classifiers to select and rank proposal segments of pre-determined boundaries. However, a desirable model should move beyond segment-level and make dense predictions at a fine granularity in time to determine precise temporal boundaries. To this end, we design a novel Convolutional-De-Convolutional (CDC) network that places CDC filters on top of 3D ConvNets, which have been shown to be effective for abstracting action semantics but reduce the temporal length of the input data. The proposed CDC filter performs the required temporal upsampling and spatial downsampling operations simultaneously to predict actions at the frame-level granularity. It is unique in jointly modeling action semantics in space-time and fine-grained temporal dynamics. We train the CDC network in an end-to-end manner efficiently. Our model not only achieves superior performance in detecting actions in every frame, but also significantly boosts the precision of localizing temporal boundaries. Finally, the CDC network demonstrates a very high efficiency with the ability to process 500 frames per second on a single GPU server. We will update the camera-ready version and publish the source codes online soon.
Tasks	Action Localization, Temporal Action Localization
Published	2017-03-04
URL	http://arxiv.org/abs/1703.01515v2
PDF	http://arxiv.org/pdf/1703.01515v2.pdf
PWC	https://paperswithcode.com/paper/cdc-convolutional-de-convolutional-networks
Repo
Framework

Modeling Image Virality with Pairwise Spatial Transformer Networks


Title	Modeling Image Virality with Pairwise Spatial Transformer Networks
Authors	Abhimanyu Dubey, Sumeet Agarwal
Abstract	The study of virality and information diffusion online is a topic gaining traction rapidly in the computational social sciences. Computer vision and social network analysis research have also focused on understanding the impact of content and information diffusion in making content viral, with prior approaches not performing significantly well as other traditional classification tasks. In this paper, we present a novel pairwise reformulation of the virality prediction problem as an attribute prediction task and develop a novel algorithm to model image virality on online media using a pairwise neural network. Our model provides significant insights into the features that are responsible for promoting virality and surpasses the existing state-of-the-art by a 12% average improvement in prediction. We also investigate the effect of external category supervision on relative attribute prediction and observe an increase in prediction accuracy for the same across several attribute learning datasets.
Tasks
Published	2017-09-22
URL	http://arxiv.org/abs/1709.07914v1
PDF	http://arxiv.org/pdf/1709.07914v1.pdf
PWC	https://paperswithcode.com/paper/modeling-image-virality-with-pairwise-spatial
Repo
Framework

Near-Optimal Closeness Testing of Discrete Histogram Distributions


Title	Near-Optimal Closeness Testing of Discrete Histogram Distributions
Authors	Ilias Diakonikolas, Daniel M. Kane, Vladimir Nikishkin
Abstract	We investigate the problem of testing the equivalence between two discrete histograms. A {\em $k$-histogram} over $[n]$ is a probability distribution that is piecewise constant over some set of $k$ intervals over $[n]$. Histograms have been extensively studied in computer science and statistics. Given a set of samples from two $k$-histogram distributions $p, q$ over $[n]$, we want to distinguish (with high probability) between the cases that $p = q$ and $\p-q_1 \geq \epsilon$. The main contribution of this paper is a new algorithm for this testing problem and a nearly matching information-theoretic lower bound. Specifically, the sample complexity of our algorithm matches our lower bound up to a logarithmic factor, improving on previous work by polynomial factors in the relevant parameters. Our algorithmic approach applies in a more general setting and yields improved sample upper bounds for testing closeness of other structured distributions as well.
Tasks
Published	2017-03-06
URL	http://arxiv.org/abs/1703.01913v1
PDF	http://arxiv.org/pdf/1703.01913v1.pdf
PWC	https://paperswithcode.com/paper/near-optimal-closeness-testing-of-discrete
Repo
Framework

Interactive Learning of State Representation through Natural Language Instruction and Explanation


Title	Interactive Learning of State Representation through Natural Language Instruction and Explanation
Authors	Qiaozi Gao, Lanbo She, Joyce Y. Chai
Abstract	One significant simplification in most previous work on robot learning is the closed-world assumption where the robot is assumed to know ahead of time a complete set of predicates describing the state of the physical world. However, robots are not likely to have a complete model of the world especially when learning a new task. To address this problem, this extended abstract gives a brief introduction to our on-going work that aims to enable the robot to acquire new state representations through language communication with humans.
Tasks
Published	2017-10-07
URL	http://arxiv.org/abs/1710.02714v1
PDF	http://arxiv.org/pdf/1710.02714v1.pdf
PWC	https://paperswithcode.com/paper/interactive-learning-of-state-representation
Repo
Framework

Multilayer tensor factorization with applications to recommender systems


Title	Multilayer tensor factorization with applications to recommender systems
Authors	Xuan Bi, Annie Qu, Xiaotong Shen
Abstract	Recommender systems have been widely adopted by electronic commerce and entertainment industries for individualized prediction and recommendation, which benefit consumers and improve business intelligence. In this article, we propose an innovative method, namely the recommendation engine of multilayers (REM), for tensor recommender systems. The proposed method utilizes the structure of a tensor response to integrate information from multiple modes, and creates an additional layer of nested latent factors to accommodate between-subjects dependency. One major advantage is that the proposed method is able to address the “cold-start” issue in the absence of information from new customers, new products or new contexts. Specifically, it provides more effective recommendations through sub-group information. To achieve scalable computation, we develop a new algorithm for the proposed method, which incorporates a maximum block improvement strategy into the cyclic blockwise-coordinate-descent algorithm. In theory, we investigate both algorithmic properties for global and local convergence, along with the asymptotic consistency of estimated parameters. Finally, the proposed method is applied in simulations and IRI marketing data with 116 million observations of product sales. Numerical studies demonstrate that the proposed method outperforms existing competitors in the literature.
Tasks	Recommendation Systems
Published	2017-11-05
URL	http://arxiv.org/abs/1711.01598v1
PDF	http://arxiv.org/pdf/1711.01598v1.pdf
PWC	https://paperswithcode.com/paper/multilayer-tensor-factorization-with
Repo
Framework