October 16, 2019

3087 words 15 mins read

Paper Group ANR 1081

Cross-modality deep learning brings bright-field microscopy contrast to holography. Towards Learning Sparsely Used Dictionaries with Arbitrary Supports. On the Winograd Schema: Situating Language Understanding in the Data-Information-Knowledge Continuum. Dictionary learning - from local towards global and adaptive. Towards Understanding Limitations …

Cross-modality deep learning brings bright-field microscopy contrast to holography


Title	Cross-modality deep learning brings bright-field microscopy contrast to holography
Authors	Yichen Wu, Yilin Luo, Gunvant Chaudhari, Yair Rivenson, Ayfer Calis, Kevin De Haan, Aydogan Ozcan
Abstract	Deep learning brings bright-field microscopy contrast to holographic images of a sample volume, bridging the volumetric imaging capability of holography with the speckle- and artifact-free image contrast of bright-field incoherent microscopy.
Tasks
Published	2018-11-17
URL	http://arxiv.org/abs/1811.07103v1
PDF	http://arxiv.org/pdf/1811.07103v1.pdf
PWC	https://paperswithcode.com/paper/cross-modality-deep-learning-brings-bright
Repo
Framework

Towards Learning Sparsely Used Dictionaries with Arbitrary Supports


Title	Towards Learning Sparsely Used Dictionaries with Arbitrary Supports
Authors	Pranjal Awasthi, Aravindan Vijayaraghavan
Abstract	Dictionary learning is a popular approach for inferring a hidden basis or dictionary in which data has a sparse representation. Data generated from the dictionary A (an n by m matrix, with m > n in the over-complete setting) is given by Y = AX where X is a matrix whose columns have supports chosen from a distribution over k-sparse vectors, and the non-zero values chosen from a symmetric distribution. Given Y, the goal is to recover A and X in polynomial time. Existing algorithms give polytime guarantees for recovering incoherent dictionaries, under strong distributional assumptions both on the supports of the columns of X, and on the values of the non-zero entries. In this work, we study the following question: Can we design efficient algorithms for recovering dictionaries when the supports of the columns of X are arbitrary? To address this question while circumventing the issue of non-identifiability, we study a natural semirandom model for dictionary learning where there are a large number of samples $y=Ax$ with arbitrary k-sparse supports for x, along with a few samples where the sparse supports are chosen uniformly at random. While the few samples with random supports ensures identifiability, the support distribution can look almost arbitrary in aggregate. Hence existing algorithmic techniques seem to break down as they make strong assumptions on the supports. Our main contribution is a new polynomial time algorithm for learning incoherent over-complete dictionaries that works under the semirandom model. Additionally the same algorithm provides polynomial time guarantees in new parameter regimes when the supports are fully random. Finally using these techniques, we also identify a minimal set of conditions on the supports under which the dictionary can be (information theoretically) recovered from polynomial samples for almost linear sparsity, i.e., $k=\tilde{O}(n)$.
Tasks	Dictionary Learning
Published	2018-04-23
URL	http://arxiv.org/abs/1804.08603v2
PDF	http://arxiv.org/pdf/1804.08603v2.pdf
PWC	https://paperswithcode.com/paper/towards-learning-sparsely-used-dictionaries
Repo
Framework

On the Winograd Schema: Situating Language Understanding in the Data-Information-Knowledge Continuum


Title	On the Winograd Schema: Situating Language Understanding in the Data-Information-Knowledge Continuum
Authors	Walid S. Saba
Abstract	The Winograd Schema (WS) challenge, proposed as an al-ternative to the Turing Test, has become the new standard for evaluating progress in natural language understanding (NLU). In this paper we will not however be concerned with how this challenge might be addressed. Instead, our aim here is threefold: (i) we will first formally ‘situate’ the WS challenge in the data-information-knowledge continuum, suggesting where in that continuum a good WS resides; (ii) we will show that a WS is just special case of a more general phenomenon in language understanding, namely the missing text phenomenon (henceforth, MTP) - in particular, we will argue that what we usually call thinking in the process of language understanding involves discovering a significant amount of ‘missing text’ - text that is not explicitly stated, but is often implicitly assumed as shared background knowledge; and (iii) we conclude by a brief discussion on why MTP is inconsistent with the data-driven and machine learning approach to language understanding.
Tasks
Published	2018-09-30
URL	http://arxiv.org/abs/1810.00324v3
PDF	http://arxiv.org/pdf/1810.00324v3.pdf
PWC	https://paperswithcode.com/paper/on-the-winograd-schema-situating-language
Repo
Framework

Dictionary learning - from local towards global and adaptive


Title	Dictionary learning - from local towards global and adaptive
Authors	Karin Schnass
Abstract	This paper studies the convergence behaviour of dictionary learning via the Iterative Thresholding and K-residual Means (ITKrM) algorithm. On one hand it is shown that there exist stable fixed points that do not correspond to the generating dictionary, which can be characterised as very coherent. On the other hand it is proved that ITKrM is a contraction under much relaxed conditions than previously necessary. Based on the characterisation of the stable fixed points, replacing coherent atoms with carefully designed replacement candidates is proposed. In experiments on synthetic data this outperforms random or no replacement and always leads to full dictionary recovery. Finally the question how to learn dictionaries without knowledge of the correct dictionary size and sparsity level is addressed. Decoupling the replacement strategy of coherent or unused atoms into pruning and adding, and slowly carefully increasing the sparsity level, leads to an adaptive version of ITKrM. In several experiments this adaptive dictionary learning algorithm is shown to recover a generating dictionary from randomly initialised dictionaries of various sizes on synthetic data and to learn meaningful dictionaries on image data.
Tasks	Dictionary Learning
Published	2018-04-19
URL	http://arxiv.org/abs/1804.07101v2
PDF	http://arxiv.org/pdf/1804.07101v2.pdf
PWC	https://paperswithcode.com/paper/dictionary-learning-from-local-towards-global
Repo
Framework

Towards Understanding Limitations of Pixel Discretization Against Adversarial Attacks


Title	Towards Understanding Limitations of Pixel Discretization Against Adversarial Attacks
Authors	Jiefeng Chen, Xi Wu, Vaibhav Rastogi, Yingyu Liang, Somesh Jha
Abstract	Wide adoption of artificial neural networks in various domains has led to an increasing interest in defending adversarial attacks against them. Preprocessing defense methods such as pixel discretization are particularly attractive in practice due to their simplicity, low computational overhead, and applicability to various systems. It is observed that such methods work well on simple datasets like MNIST, but break on more complicated ones like ImageNet under recently proposed strong white-box attacks. To understand the conditions for success and potentials for improvement, we study the pixel discretization defense method, including more sophisticated variants that take into account the properties of the dataset being discretized. Our results again show poor resistance against the strong attacks. We analyze our results in a theoretical framework and offer strong evidence that pixel discretization is unlikely to work on all but the simplest of the datasets. Furthermore, our arguments present insights why some other preprocessing defenses may be insecure.
Tasks
Published	2018-05-20
URL	https://arxiv.org/abs/1805.07816v5
PDF	https://arxiv.org/pdf/1805.07816v5.pdf
PWC	https://paperswithcode.com/paper/towards-understanding-limitations-of-pixel
Repo
Framework

Binary Matrix Factorization via Dictionary Learning


Title	Binary Matrix Factorization via Dictionary Learning
Authors	Ignacio Ramirez
Abstract	Matrix factorization is a key tool in data analysis; its applications include recommender systems, correlation analysis, signal processing, among others. Binary matrices are a particular case which has received significant attention for over thirty years, especially within the field of data mining. Dictionary learning refers to a family of methods for learning overcomplete basis (also called frames) in order to efficiently encode samples of a given type; this area, now also about twenty years old, was mostly developed within the signal processing field. In this work we propose two binary matrix factorization methods based on a binary adaptation of the dictionary learning paradigm to binary matrices. The proposed algorithms focus on speed and scalability; they work with binary factors combined with bit-wise operations and a few auxiliary integer ones. Furthermore, the methods are readily applicable to online binary matrix factorization. Another important issue in matrix factorization is the choice of rank for the factors; we address this model selection problem with an efficient method based on the Minimum Description Length principle. Our preliminary results show that the proposed methods are effective at producing interpretable factorizations of various data types of different nature.
Tasks	Dictionary Learning, Model Selection, Recommendation Systems
Published	2018-04-16
URL	http://arxiv.org/abs/1804.05482v2
PDF	http://arxiv.org/pdf/1804.05482v2.pdf
PWC	https://paperswithcode.com/paper/binary-matrix-factorization-via-dictionary
Repo
Framework

Learning to Segment via Cut-and-Paste


Title	Learning to Segment via Cut-and-Paste
Authors	Tal Remez, Jonathan Huang, Matthew Brown
Abstract	This paper presents a weakly-supervised approach to object instance segmentation. Starting with known or predicted object bounding boxes, we learn object masks by playing a game of cut-and-paste in an adversarial learning setup. A mask generator takes a detection box and Faster R-CNN features, and constructs a segmentation mask that is used to cut-and-paste the object into a new image location. The discriminator tries to distinguish between real objects, and those cut and pasted via the generator, giving a learning signal that leads to improved object masks. We verify our method experimentally using Cityscapes, COCO, and aerial image datasets, learning to segment objects without ever having seen a mask in training. Our method exceeds the performance of existing weakly supervised methods, without requiring hand-tuned segment proposals, and reaches 90% of supervised performance.
Tasks	Instance Segmentation, Semantic Segmentation
Published	2018-03-16
URL	http://arxiv.org/abs/1803.06414v1
PDF	http://arxiv.org/pdf/1803.06414v1.pdf
PWC	https://paperswithcode.com/paper/learning-to-segment-via-cut-and-paste
Repo
Framework

Question Type Guided Attention in Visual Question Answering


Title	Question Type Guided Attention in Visual Question Answering
Authors	Yang Shi, Tommaso Furlanello, Sheng Zha, Animashree Anandkumar
Abstract	Visual Question Answering (VQA) requires integration of feature maps with drastically different structures and focus of the correct regions. Image descriptors have structures at multiple spatial scales, while lexical inputs inherently follow a temporal sequence and naturally cluster into semantically different question types. A lot of previous works use complex models to extract feature representations but neglect to use high-level information summary such as question types in learning. In this work, we propose Question Type-guided Attention (QTA). It utilizes the information of question type to dynamically balance between bottom-up and top-down visual features, respectively extracted from ResNet and Faster R-CNN networks. We experiment with multiple VQA architectures with extensive input ablation studies over the TDIUC dataset and show that QTA systematically improves the performance by more than 5% across multiple question type categories such as “Activity Recognition”, “Utility” and “Counting” on TDIUC dataset. By adding QTA on the state-of-art model MCB, we achieve 3% improvement for overall accuracy. Finally, we propose a multi-task extension to predict question types which generalizes QTA to applications that lack of question type, with minimal performance loss.
Tasks	Activity Recognition, Question Answering, Visual Question Answering
Published	2018-04-06
URL	http://arxiv.org/abs/1804.02088v2
PDF	http://arxiv.org/pdf/1804.02088v2.pdf
PWC	https://paperswithcode.com/paper/question-type-guided-attention-in-visual
Repo
Framework

Improve Uncertainty Estimation for Unknown Classes in Bayesian Neural Networks with Semi-Supervised /One Set Classification


Title	Improve Uncertainty Estimation for Unknown Classes in Bayesian Neural Networks with Semi-Supervised /One Set Classification
Authors	Buu Phan
Abstract	Although deep neural network (DNN) has achieved many state-of-the-art results, estimating the uncertainty presented in the DNN model and the data is a challenging task. Problems related to uncertainty such as classifying unknown classes (class which does not appear in the training data) data as known class with high confidence, is critically concerned in the safety domain area (e.g, autonomous driving, medical diagnosis). In this paper, we show that applying current Bayesian Neural Network (BNN) techniques alone does not effectively capture the uncertainty. To tackle this problem, we introduce a simple way to improve the BNN by using one class classification (in this paper, we use the term “set classification” instead). We empirically show the result of our method on an experiment which involves three datasets: MNIST, notMNIST and FMNIST.
Tasks	Autonomous Driving, Medical Diagnosis
Published	2018-05-04
URL	http://arxiv.org/abs/1805.01955v2
PDF	http://arxiv.org/pdf/1805.01955v2.pdf
PWC	https://paperswithcode.com/paper/improve-uncertainty-estimation-for-unknown
Repo
Framework

Dissimilarity-based representation for radiomics applications


Title	Dissimilarity-based representation for radiomics applications
Authors	Hongliu Cao, Simon Bernard, Laurent Heutte, Robert Sabourin
Abstract	Radiomics is a term which refers to the analysis of the large amount of quantitative tumor features extracted from medical images to find useful predictive, diagnostic or prognostic information. Many recent studies have proved that radiomics can offer a lot of useful information that physicians cannot extract from the medical images and can be associated with other information like gene or protein data. However, most of the classification studies in radiomics report the use of feature selection methods without identifying the machine learning challenges behind radiomics. In this paper, we first show that the radiomics problem should be viewed as an high dimensional, low sample size, multi view learning problem, then we compare different solutions proposed in multi view learning for classifying radiomics data. Our experiments, conducted on several real world multi view datasets, show that the intermediate integration methods work significantly better than filter and embedded feature selection methods commonly used in radiomics.
Tasks	Feature Selection, MULTI-VIEW LEARNING
Published	2018-03-12
URL	http://arxiv.org/abs/1803.04460v1
PDF	http://arxiv.org/pdf/1803.04460v1.pdf
PWC	https://paperswithcode.com/paper/dissimilarity-based-representation-for
Repo
Framework

White matter fiber analysis using kernel dictionary learning and sparsity priors


Title	White matter fiber analysis using kernel dictionary learning and sparsity priors
Authors	Kuldeep Kumar, Kaleem Siddiqi, Christian Desrosiers
Abstract	Diffusion magnetic resonance imaging, a non-invasive tool to infer white matter fiber connections, produces a large number of streamlines containing a wealth of information on structural connectivity. The size of these tractography outputs makes further analyses complex, creating a need for methods to group streamlines into meaningful bundles. In this work, we address this by proposing a set of kernel dictionary learning and sparsity priors based methods. Proposed frameworks include L-0 norm, group sparsity, as well as manifold regularization prior. The proposed methods allow streamlines to be assigned to more than one bundle, making it more robust to overlapping bundles and inter-subject variations. We evaluate the performance of our method on a labeled set and data from Human Connectome Project. Results highlight the ability of our method to group streamlines into plausible bundles and illustrate the impact of sparsity priors on the performance of the proposed methods.
Tasks	Dictionary Learning
Published	2018-04-15
URL	http://arxiv.org/abs/1804.05427v1
PDF	http://arxiv.org/pdf/1804.05427v1.pdf
PWC	https://paperswithcode.com/paper/white-matter-fiber-analysis-using-kernel
Repo
Framework

Lightweight Pyramid Networks for Image Deraining


Title	Lightweight Pyramid Networks for Image Deraining
Authors	Xueyang Fu, Borong Liang, Yue Huang, Xinghao Ding, John Paisley
Abstract	Existing deep convolutional neural networks have found major success in image deraining, but at the expense of an enormous number of parameters. This limits their potential application, for example in mobile devices. In this paper, we propose a lightweight pyramid of networks (LPNet) for single image deraining. Instead of designing a complex network structures, we use domain-specific knowledge to simplify the learning process. Specifically, we find that by introducing the mature Gaussian-Laplacian image pyramid decomposition technology to the neural network, the learning problem at each pyramid level is greatly simplified and can be handled by a relatively shallow network with few parameters. We adopt recursive and residual network structures to build the proposed LPNet, which has less than 8K parameters while still achieving state-of-the-art performance on rain removal. We also discuss the potential value of LPNet for other low- and high-level vision tasks.
Tasks	Rain Removal, Single Image Deraining
Published	2018-05-16
URL	http://arxiv.org/abs/1805.06173v1
PDF	http://arxiv.org/pdf/1805.06173v1.pdf
PWC	https://paperswithcode.com/paper/lightweight-pyramid-networks-for-image
Repo
Framework

Robust Video Content Alignment and Compensation for Clear Vision Through the Rain


Title	Robust Video Content Alignment and Compensation for Clear Vision Through the Rain
Authors	Jie Chen, Cheen-Hau Tan, Junhui Hou, Lap-Pui Chau, He Li
Abstract	Outdoor vision-based systems suffer from atmospheric turbulences, and rain is one of the worst factors for vision degradation. Current rain removal methods show limitations either for complex dynamic scenes, or under torrential rain with opaque occlusions. We propose a novel derain framework which applies superpixel (SP) segmentation to decompose the scene into depth consistent units. Alignment of scene contents are done at the SP level, which proves to be robust against rain occlusion interferences and fast camera motion. Two alignment output tensors, i.e., optimal temporal match tensor and sorted spatial-temporal match tensor, provide informative clues for the location of rain streaks and the occluded background contents. Different classical and novel methods such as Robust Principle Component Analysis and Convolutional Neural Networks are applied and compared for their respective advantages in efficiently exploiting the rich spatial-temporal features provided by the two tensors. Extensive evaluations show that advantage of up to 5dB is achieved on the scene restoration PSNR over state-of-the-art methods, and the advantage is especially obvious with highly complex and dynamic scenes. Visual evaluations show that the proposed framework is not only able to suppress heavy and opaque occluding rain streaks, but also large semi-transparent regional fluctuations and distortions.
Tasks	Rain Removal
Published	2018-04-24
URL	http://arxiv.org/abs/1804.09555v1
PDF	http://arxiv.org/pdf/1804.09555v1.pdf
PWC	https://paperswithcode.com/paper/robust-video-content-alignment-and
Repo
Framework

Residual-Guide Feature Fusion Network for Single Image Deraining


Title	Residual-Guide Feature Fusion Network for Single Image Deraining
Authors	Zhiwen Fan, Huafeng Wu, Xueyang Fu, Yue Hunag, Xinghao Ding
Abstract	Single image rain streaks removal is extremely important since rainy images adversely affect many computer vision systems. Deep learning based methods have found great success in image deraining tasks. In this paper, we propose a novel residual-guide feature fusion network, called ResGuideNet, for single image deraining that progressively predicts highquality reconstruction. Specifically, we propose a cascaded network and adopt residuals generated from shallower blocks to guide deeper blocks. By using this strategy, we can obtain a coarse to fine estimation of negative residual as the blocks go deeper. The outputs of different blocks are merged into the final reconstruction. We adopt recursive convolution to build each block and apply supervision to all intermediate results, which enable our model to achieve promising performance on synthetic and real-world data while using fewer parameters than previous required. ResGuideNet is detachable to meet different rainy conditions. For images with light rain streaks and limited computational resource at test time, we can obtain a decent performance even with several building blocks. Experiments validate that ResGuideNet can benefit other low- and high-level vision tasks.
Tasks	Rain Removal, Single Image Deraining
Published	2018-04-20
URL	http://arxiv.org/abs/1804.07493v1
PDF	http://arxiv.org/pdf/1804.07493v1.pdf
PWC	https://paperswithcode.com/paper/residual-guide-feature-fusion-network-for
Repo
Framework

Matrix Completion from Non-Uniformly Sampled Entries


Title	Matrix Completion from Non-Uniformly Sampled Entries
Authors	Yuanyu Wan, Jinfeng Yi, Lijun Zhang
Abstract	In this paper, we consider matrix completion from non-uniformly sampled entries including fully observed and partially observed columns. Specifically, we assume that a small number of columns are randomly selected and fully observed, and each remaining column is partially observed with uniform sampling. To recover the unknown matrix, we first recover its column space from the fully observed columns. Then, for each partially observed column, we recover it by finding a vector which lies in the recovered column space and consists of the observed entries. When the unknown $m\times n$ matrix is low-rank, we show that our algorithm can exactly recover it from merely $\Omega(rn\ln n)$ entries, where $r$ is the rank of the matrix. Furthermore, for a noisy low-rank matrix, our algorithm computes a low-rank approximation of the unknown matrix and enjoys an additive error bound measured by Frobenius norm. Experimental results on synthetic datasets verify our theoretical claims and demonstrate the effectiveness of our proposed algorithm.
Tasks	Matrix Completion
Published	2018-06-27
URL	http://arxiv.org/abs/1806.10308v1
PDF	http://arxiv.org/pdf/1806.10308v1.pdf
PWC	https://paperswithcode.com/paper/matrix-completion-from-non-uniformly-sampled
Repo
Framework