Efficient and Parallel Separable Dictionary Learning

• URL: http://arxiv.org/abs/2007.03800v4
• Date: Wed, 1 Dec 2021 22:50:00 GMT
• Title: Efficient and Parallel Separable Dictionary Learning
• Authors: Cristian Rusu and Paul Irofti
• Abstract summary: We describe a highly parallelizable algorithm that learns such dictionaries. We highlight the performance of the proposed method to sparsely represent image and hyperspectral data, and for image denoising.
• Score: 2.6905021039717987
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Separable, or Kronecker product, dictionaries provide natural decompositions for 2D signals, such as images. In this paper, we describe a highly parallelizable algorithm that learns such dictionaries which reaches sparse representations competitive with the previous state of the art dictionary learning algorithms from the literature but at a lower computational cost. We highlight the performance of the proposed method to sparsely represent image and hyperspectral data, and for image denoising.

Related papers

• Convergence of alternating minimisation algorithms for dictionary learning [4.5687771576879594]
  We derive sufficient conditions for the convergence of two popular alternating minimisation algorithms for dictionary learning. We show that given a well-behaved initialisation that is either within distance at most $1/log(K)$ to the generating dictionary or has a special structure ensuring that each element of the initialisation only points to one generating element, both algorithms will converge with geometric convergence rate to the generating dictionary.
  arXiv  Detail & Related papers  (2023-04-04T12:58:47Z)
• Describing Sets of Images with Textual-PCA [89.46499914148993]
  We seek to semantically describe a set of images, capturing both the attributes of single images and the variations within the set. Our procedure is analogous to Principle Component Analysis, in which the role of projection vectors is replaced with generated phrases.
  arXiv  Detail & Related papers  (2022-10-21T17:10:49Z)
• Efficient Image Denoising by Low-Rank Singular Vector Approximations of Geodesics' Gramian Matrix [2.3499129784547654]
  Noise contamination of images results in substandard expectations among the people. Image denoising is an essential pre-processing step. We present a manifold-based noise filtering method that mainly exploits a few prominent singular vectors of the geodesics' Gramian matrix.
  arXiv  Detail & Related papers  (2022-09-27T01:03:36Z)
• Two-stream Hierarchical Similarity Reasoning for Image-text Matching [66.43071159630006]
  A hierarchical similarity reasoning module is proposed to automatically extract context information. Previous approaches only consider learning single-stream similarity alignment. A two-stream architecture is developed to decompose image-text matching into image-to-text level and text-to-image level similarity computation.
  arXiv  Detail & Related papers  (2022-03-10T12:56:10Z)
• Deep learning based dictionary learning and tomographic image reconstruction [0.0]
  This work presents an approach for image reconstruction in clinical low-dose tomography that combines principles from sparse signal processing with ideas from deep learning. First, we describe sparse signal representation in terms of dictionaries from a statistical perspective and interpret dictionary learning as a process of aligning distribution that arises from a generative model with empirical distribution of true signals. As a result we can see that sparse coding with learned dictionaries resembles a specific variational autoencoder, where the decoder is a linear function and the encoder is a sparse coding algorithm.
  arXiv  Detail & Related papers  (2021-08-26T12:10:17Z)
• Exact Sparse Orthogonal Dictionary Learning [8.577876545575828]
  We find that our method can result in better denoising results than over-complete dictionary based learning methods. Our method has the additional advantage of high efficiency.
  arXiv  Detail & Related papers  (2021-03-14T07:51:32Z)
• Learning Spatial and Spatio-Temporal Pixel Aggregations for Image and Video Denoising [104.59305271099967]
  We present a pixel aggregation network and learn the pixel sampling and averaging strategies for image denoising. We develop a pixel aggregation network for video denoising to sample pixels across the spatial-temporal space. Our method is able to solve the misalignment issues caused by large motion in dynamic scenes.
  arXiv  Detail & Related papers  (2021-01-26T13:00:46Z)
• Accurate Word Representations with Universal Visual Guidance [55.71425503859685]
  This paper proposes a visual representation method to explicitly enhance conventional word embedding with multiple-aspect senses from visual guidance. We build a small-scale word-image dictionary from a multimodal seed dataset where each word corresponds to diverse related images. Experiments on 12 natural language understanding and machine translation tasks further verify the effectiveness and the generalization capability of the proposed approach.
  arXiv  Detail & Related papers  (2020-12-30T09:11:50Z)
• Lightweight Generative Adversarial Networks for Text-Guided Image Manipulation [139.41321867508722]
  We propose a novel lightweight generative adversarial network for efficient image manipulation using natural language descriptions. A new word-level discriminator is proposed, which provides the generator with fine-grained training feedback at word-level.
  arXiv  Detail & Related papers  (2020-10-23T02:43:02Z)
• Blind Face Restoration via Deep Multi-scale Component Dictionaries [75.02640809505277]
  We propose a deep face dictionary network (termed as DFDNet) to guide the restoration process of degraded observations. DFDNet generates deep dictionaries for perceptually significant face components from high-quality images. component AdaIN is leveraged to eliminate the style diversity between the input and dictionary features.
  arXiv  Detail & Related papers  (2020-08-02T07:02:07Z)
• Contrast-weighted Dictionary Learning Based Saliency Detection for Remote Sensing Images [3.338193485961624]
  We propose a novel saliency detection model based on Contrast-weighted Dictionary Learning (CDL) for remote sensing images. Specifically, the proposed CDL learns salient and non-salient atoms from positive and negative samples to construct a discriminant dictionary. By using the proposed joint saliency measure, a variety of saliency maps are generated based on the discriminant dictionary.
  arXiv  Detail & Related papers  (2020-04-06T06:49:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.