SOURCE-LINKED INTELLIGENCE

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

arXiv · AI, language, vision and robotics · article · Sep 16, 2026 · UTC

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 learne

Read original source ↗ Open in workspace

recordType

paper

region

Global