Training-Adaptive Convolutional Sparse Coding via Information Bottleneck for Robust Visual Representation

Hugging Face Daily Papers Papers
convolutional-sparse-coding information-bottleneck visual-representation robustness training-adaptive computer-vision deep-learning

Summary

This paper proposes a training-adaptive convolutional sparse coding framework that leverages information bottleneck principles for robust visual representation, achieving improved performance on CIFAR and ImageNet under input perturbations.

Visual signals require compact yet sufficient representations for robust downstream prediction. Convolutional sparse coding (CSC) provides an explicit mechanism for suppressing redundant components while preserving signal content, but its sparsity coefficient is typically fixed and manually selected. We propose a training-adaptive convolutional sparse coding framework for robust visual signal representation. Specifically, we unfold the CSC optimization with the Fast Iterative Shrinkage-Thresholding Algorithm (FISTA) and treat the sparsity coefficient as a differentiable variable jointly learned with the network parameters. From the information bottleneck perspective, this coefficient controls the trade-off between information retention and compression: the sparsity term promotes compact representations, while the reconstruction term together with task loss preserves task-relevant signal content. We further introduce a label-free post-training strategy that adjusts the compression strength for corrupted inputs with the main network parameters fixed. Experiments on CIFAR and ImageNet demonstrate competitive clean-data recognition and greatly improved robustness under different input perturbations.
Original Article
View Cached Full Text

Cached at: 09/21/26, 07:20 AM

Paper page - Training-Adaptive Convolutional Sparse Coding via Information Bottleneck for Robust Visual Representation

Source: https://huggingface.co/papers/2609.19122

Abstract

Visualsignalsrequirecompactyetsufficientrepresentationsforrobustdownstreamprediction.Convolutionalsparsecoding(CSC)providesanexplicitmechanismforsuppressingredundantcomponentswhilepreservingsignalcontent,butitssparsitycoefficientistypicallyfixedandmanuallyselected.Weproposeatraining-adaptiveconvolutionalsparsecodingframeworkforrobustvisualsignalrepresentation.Specifically,weunfoldtheCSCoptimizationwiththeFastIterativeShrinkage-ThresholdingAlgorithm(FISTA)andtreatthesparsitycoefficientasadifferentiablevariablejointlylearnedwiththenetworkparameters.Fromtheinformationbottleneckperspective,thiscoefficientcontrolsthetrade-offbetweeninformationretentionandcompression:thesparsitytermpromotescompactrepresentations,whilethereconstructiontermtogetherwithtasklosspreservestask-relevantsignalcontent.Wefurtherintroducealabel-freepost-trainingstrategythatadjuststhecompressionstrengthforcorruptedinputswiththemainnetworkparametersfixed.ExperimentsonCIFARandImageNetdemonstratecompetitiveclean-datarecognitionandgreatlyimprovedrobustnessunderdifferentinputperturbations.

View arXiv pageView PDFGitHub0Add to collection

Get this paper in your agent:

hf papers read 2609\.19122

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2609.19122 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2609.19122 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2609.19122 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

Hoeffding Concept Bottleneck Models with Applications to Overhead Images

arXiv cs.LG

Introduces Hoeffding Concept Bottleneck Models (HCBM), a nonlinear and sparse aggregation of concept scores using Hoeffding functional decomposition of gradient-boosted trees, for improved explainability and accuracy in classification and object detection tasks, with applications to overhead images.