Firehose

17 SEP 2026 · Paper

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

This paper develops a new method for creating robust visual representations in images, which can better handle noisy or distorted data, and improves the performance of downstream tasks such as image classification. Practitioners might care about this approach as it can enhance the robustness of image recognition systems in real-world applications.

convolutional sparse coding information bottleneck robust visual representation deep learning computer vision

Browse by tag

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