Metraipolis › archive › dc_4fbb07bbbd53

Training-Adaptive Convolutional Sparse Coding via Information Bottleneck for Robust Visual Representation — arXiv:2609.19122

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.19122
License (as archived): CC0-1.0
Archived: 2026-10-10T01:45:23.541Z
SHA-256 of the archived text: dee24d4dbffc2cfd9df701c55cbb4ecfbd72877ebceb43b5739fd2809b775d0b
Stable URL of this page: https://metraipolis.com/documento/dc_4fbb07bbbd53

How to cite

Training-Adaptive Convolutional Sparse Coding via Information Bottleneck for Robust Visual Representation — arXiv:2609.19122 — arXiv (en), https://arxiv.org/abs/2609.19122 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4fbb07bbbd53 (Metraipolis archive dc_4fbb07bbbd53, sha256 dee24d4dbffc2cfd9df701c55cbb4ecfbd72877ebceb43b5739fd2809b775d0b)

BibTeX

@misc{dc4fbb07bbbd53,
  title = {Training-Adaptive Convolutional Sparse Coding via Information Bottleneck for Robust Visual Representation — arXiv:2609.19122},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.19122},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4fbb07bbbd53; sha256 dee24d4dbffc2cfd9df701c55cbb4ecfbd72877ebceb43b5739fd2809b775d0b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.19122. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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 often manually selected during training. 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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-21 in cs.LG).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG); Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2609.19122 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-10T01:14:16.676Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).