paper-with-me

Papers

Supervised Convolutional Sparse Coding

2018-04-08 · Lama Affara, Bernard Ghanem, Peter Wonka

Convolutional Sparse Coding (CSC) is a well-established image representation model especially suited for image restoration tasks. In this work, we extend the applicability of this model by proposing a supervised approach to convolutional sparse coding, which aims at learning discriminative dictionaries instead of purely reconstructive ones. We incorporate a supervised regularization term into the traditional unsupervised CSC objective to encourage the final dictionary elements to be discriminative. Experimental results show that using supervised convolutional learning results in two key advantages. First, we learn more semantically relevant filters in the dictionary and second, we achieve improved image reconstruction on unseen data.

📄 PDF Abstract BibTeX arXiv:1804.02678

Code (0)

등록된 구현이 없습니다.

Tasks

Image ReconstructionImage Restoration

Similar Papers 제목 키워드 기반

Sparse Coding on Stereo Video for Object Detection

2017-05-19 · Sheng Y. Lundquist, Melanie Mitchell, Garrett T. Kenyon

Deep Convolutional Neural Networks (DCNN) require millions of labeled training examples for image classification and object detection tasks, which restrict these models to domains where such datasets are available. In th…

image-classificationImage ClassificationObjectobject-detection+1

From biological vision to unsupervised hierarchical sparse coding

2018-12-04 · Victor Boutin, Angelo Franciosini, Franck Ruffier, Laurent U. Perrinet

The formation of connections between neural cells is emerging essentially from an unsupervised learning process. For instance, during the development of the primary visual cortex of mammals (V1), we observe the emergence…

Efficient ADMM-based Algorithms for Convolutional Sparse Coding

2021-09-07 · Farshad G. Veshki, Sergiy A. Vorobyov

Convolutional sparse coding improves on the standard sparse approximation by incorporating a global shift-invariant model. The most efficient convolutional sparse coding methods are based on the alternating direction met…

Dictionary Learning

Penalized-likelihood PET Image Reconstruction Using 3D Structural Convolutional Sparse Coding

2019-12-16 · Nuobei Xie, Kuang Gong, Ning Guo, Zhixin Qin 외

Positron emission tomography (PET) is widely used for clinical diagnosis. As PET suffers from low resolution and high noise, numerous efforts try to incorporate anatomical priors into PET image reconstruction, especially…

Image Reconstruction

A Sparse Coding Interpretation of Neural Networks and Theoretical Implications

2021-08-14 · Joshua Bowren

Neural networks, specifically deep convolutional neural networks, have achieved unprecedented performance in various computer vision tasks, but the rationale for the computations and structures of successful neural netwo…

image-classificationImage Classification