Metraipolis › archive › dc_2bf100a10e5d

OFBD: Object-Focused Background Debiasing for Long-Tailed Learning — arXiv:2609.37331

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.37331
License (as archived)
CC0-1.0
Archived
2026-10-07T18:41:10.096Z
SHA-256 of the archived text
fdbe2028de98500033b6098522119229c68a5b0017ad7a6eb732e50900b1ed09
Stable URL of this page
https://metraipolis.com/documento/dc_2bf100a10e5d

How to cite

OFBD: Object-Focused Background Debiasing for Long-Tailed Learning — arXiv:2609.37331 — arXiv (en), https://arxiv.org/abs/2609.37331 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2bf100a10e5d (Metraipolis archive dc_2bf100a10e5d, sha256 fdbe2028de98500033b6098522119229c68a5b0017ad7a6eb732e50900b1ed09)
BibTeX
@misc{dc2bf100a10e5d,
  title = {OFBD: Object-Focused Background Debiasing for Long-Tailed Learning — arXiv:2609.37331},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.37331},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2bf100a10e5d; sha256 fdbe2028de98500033b6098522119229c68a5b0017ad7a6eb732e50900b1ed09},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.37331. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Balancing performance trade-offs on long-tailed data distributions remains a long-standing challenge in visual recognition. Existing methods mainly improve tail classes through re-balancing, representation learning, or data augmentation, but the underlying cause of tail class degradation is still insufficiently explored. In this paper, we find that standard long-tailed training induces background-biased representation and optimization: tail classes suffer larger background distribution shifts and become increasingly driven by background gradients. This reveals that tail degradation is not merely caused by insufficient samples, but also by the learning of irrelevant background features. To tackle this issue, we propose Object-Focused Background Debiasing (OFBD), a framework that mitigates background bias from both distribution and optimization perspectives. Specifically, Foreground-guided CutMix preserves target-related foregrounds while diversifying complementary backgrounds, and Background-guided Feature Rectification suppresses background-biased features without learnable parameters or additional training. Extensive experiments show that our method improves overall accuracy, achieves significant tail-class gains, and can serve as a plug-in for mainstream long-tailed methods without external data or pretrained recognition models. The code is available at: this https URL

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-30 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.37331 — 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 2026-10-07T18:04:24.854Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).