Metraipolis › archive › dc_7c5ef436c157

HiRA-CAM: Preserving Fine-Grained Spatial Relevance in Gradient-Based Visual Explanations — arXiv:2608.19407

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.19407
License (as archived)
CC0-1.0
Archived
2026-10-18T11:48:37.039Z
SHA-256 of the archived text
f7ce9e5fd417fd11fade235cbddfce19c915b509b223204991f308c1ff41d09e
Stable URL of this page
https://metraipolis.com/documento/dc_7c5ef436c157

How to cite

HiRA-CAM: Preserving Fine-Grained Spatial Relevance in Gradient-Based Visual Explanations — arXiv:2608.19407 — arXiv (en), https://arxiv.org/abs/2608.19407 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7c5ef436c157 (Metraipolis archive dc_7c5ef436c157, sha256 f7ce9e5fd417fd11fade235cbddfce19c915b509b223204991f308c1ff41d09e)
BibTeX
@misc{dc7c5ef436c157,
  title = {HiRA-CAM: Preserving Fine-Grained Spatial Relevance in Gradient-Based Visual Explanations — arXiv:2608.19407},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.19407},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7c5ef436c157; sha256 f7ce9e5fd417fd11fade235cbddfce19c915b509b223204991f308c1ff41d09e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.19407. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Deep Learning models can include billions of parameters or more, making it difficult to explain their internal transformations and outputs. However, explainability is increasing in importance due to the use of AI in crucial applications. This paper focuses on the interpretability of convolutional neural networks (CNNs). Building on the popular gradient based method LayerCAM for extracting internal features in CNNs, we propose an improved method named HiRA-CAM, and show that it outperforms both LayerCAM and Grad-CAM on creating useful saliency maps for object classification. The main feature of HiRA-CAM is its adaptive use of activation maps from all the layers of the CNN to arrive at a more focused saliency map.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-21 in cs.LG).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Neural and Evolutionary Computing (cs.NE).
Pagina del lavoro: https://arxiv.org/abs/2608.19407 — 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 2026-10-18T11:47:43.361Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).