Metraipolis › archive › dc_c0c4bb8be136

IGDA-ICMH: an Importance Guided Feature and Network Dual Adaptation Framework towards Image Compression for Machine and Human Vision — arXiv:2610.41924

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.41924
License (as archived): CC0-1.0
Archived: 2026-11-03T05:47:11.571Z
SHA-256 of the archived text: 43c073399cf62084adc5ea1afb209b4d787bc3ffe265e0977bba7745787bd158
Stable URL of this page: https://metraipolis.com/documento/dc_c0c4bb8be136

How to cite

IGDA-ICMH: an Importance Guided Feature and Network Dual Adaptation Framework towards Image Compression for Machine and Human Vision — arXiv:2610.41924 — arXiv (en), https://arxiv.org/abs/2610.41924 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c0c4bb8be136 (Metraipolis archive dc_c0c4bb8be136, sha256 43c073399cf62084adc5ea1afb209b4d787bc3ffe265e0977bba7745787bd158)

BibTeX

@misc{dcc0c4bb8be136,
  title = {IGDA-ICMH: an Importance Guided Feature and Network Dual Adaptation Framework towards Image Compression for Machine and Human Vision — arXiv:2610.41924},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41924},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c0c4bb8be136; sha256 43c073399cf62084adc5ea1afb209b4d787bc3ffe265e0977bba7745787bd158},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41924. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

With the surge of machine vision applications, image compression for both machine and human vision (ICMH) has become an important research area. Existing studies mainly focus on task-specific adaptation or multi-task joint optimization, yet they often overlook the unequal contributions of different features and network layers to downstream machine vision tasks. To address this issue, we first quantitatively investigate the impact of different feature and network layers on machine vision performance, providing a principled understanding of their importance. Based on this analysis, an Importance Guided feature and network Dual Adaptation (IGDA) framework is developed for ICMH. It adopts implicit neural representation as the basic architecture and designs an efficient adaptation structure with both feature and network weight adaptation. An Importance-Guided Network Adaptation (IGNA) module is developed with a low-rank adaptation strategy to selectively adjust key network layers according to their importance in different tasks. An Importance-Guided Feature Adaptation (IGFA) module is developed with a low-rank and Kronecker product-based transform to explore the non-local property of the features in order to reduce the number of adaptation parameters. Extensive experiments on representative machine vision tasks, including image classification and object detection, demonstrate that our IGDA-ICMH framework achieves significantly better performance than the existing implicit neural representation-based methods for ICMH.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Image and Video Processing (eess.IV) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.41924 — 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 2026-11-03T05:33:32.340Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).