Metraipolis › archive › dc_9149ec596d43

Impact of color in computer and human-based object recognition under occlusion — arXiv:2611.08808

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.08808
License (as archived)
CC0-1.0
Archived
2026-11-09T22:45:06.636Z
SHA-256 of the archived text
f1630d3686d359148b4f1847bc9848f393872527c46973160d5e261bb4228ea3
Stable URL of this page
https://metraipolis.com/documento/dc_9149ec596d43

How to cite

Impact of color in computer and human-based object recognition under occlusion — arXiv:2611.08808 — arXiv (en), https://arxiv.org/abs/2611.08808 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9149ec596d43 (Metraipolis archive dc_9149ec596d43, sha256 f1630d3686d359148b4f1847bc9848f393872527c46973160d5e261bb4228ea3)
BibTeX
@misc{dc9149ec596d43,
  title = {Impact of color in computer and human-based object recognition under occlusion — arXiv:2611.08808},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.08808},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9149ec596d43; sha256 f1630d3686d359148b4f1847bc9848f393872527c46973160d5e261bb4228ea3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.08808. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Partial occlusions challenge object recognition in both human and computer vision (CV), but the impact is largely dependent on the occlusion and model design. Properties relating to color are particularly important in biological recognition and frequently leveraged for camouflage, however there are still open questions about what makes them effective and how they translate to CV. This work studies partial occlusions that create camouflage, including those that blend in with target objects or with scenes, which alter object representations in distinct ways. Experiments evaluate recognition performance on both human participants and models ranging from convolutional neural networks (CNNs) to transformers, and additional analysis is performed on models to uncover trends in processing and object representations under multiple occlusion types. Novel metrics offer explainability of model behavior under occlusion: non-occlusion precision (NOP) and non-occlusion recall (NOR) measure alignment of model activations with and without occlusion, and activation in occlusion (AIO) measures the percentage of activations that occur in occluded regions. Findings show that human recognition, and most transformers, are negatively impacted by generated camouflaging occluders, with scene-based camouflage performing worse than object-based. Classical CNNs show a strong opposite trend, performing the worst on neutral-colored occlusions, suggesting that contextually-related colors, particularly scene-based, benefit object recognition rather than disrupting shape or boundary cues. Additionally, generated camouflaging occluders for training augmentation improves robustness to unseen camouflage for selected CNN model, and occlusion metrics suggest trends about learned mechanisms. Findings have interesting implications for alignment in human and computer vision, model vulnerabilities, and explainability.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2611.08808 — 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 2026-11-09T22:37:47.203Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).