Metraipolis › archive › dc_2ccbc93a1acf

CLEAR: Class-wise Expert Aggregation with Structured Sampling for Long-Tailed Classification — arXiv:2608.11287

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.11287
License (as archived)
CC0-1.0
Archived
2026-10-19T05:15:45.137Z
SHA-256 of the archived text
221d0f3a38968976ca26fee7f5aa42f30fc99560c5f321c007b164117ba8eef3
Stable URL of this page
https://metraipolis.com/documento/dc_2ccbc93a1acf

How to cite

CLEAR: Class-wise Expert Aggregation with Structured Sampling for Long-Tailed Classification — arXiv:2608.11287 — arXiv (en), https://arxiv.org/abs/2608.11287 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2ccbc93a1acf (Metraipolis archive dc_2ccbc93a1acf, sha256 221d0f3a38968976ca26fee7f5aa42f30fc99560c5f321c007b164117ba8eef3)
BibTeX
@misc{dc2ccbc93a1acf,
  title = {CLEAR: Class-wise Expert Aggregation with Structured Sampling for Long-Tailed Classification — arXiv:2608.11287},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.11287},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2ccbc93a1acf; sha256 221d0f3a38968976ca26fee7f5aa42f30fc99560c5f321c007b164117ba8eef3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.11287. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Long-tailed classification poses a reliability challenge because models trained on imbalanced data are unevenly reliable across frequent and underrepresented classes. While existing methods address imbalance through re-balancing, adjustment, representation learning, or multi-expert modeling, they rarely estimate which expert should be trusted for each class. This paper proposes CLEAR (Class-wise reLiability-aware Expert Aggregation for long-tailed Recognition), a modular ensemble framework for long-tailed classification. CLEAR generates diverse experts through threshold-based structured sampling while preserving the full label space, then estimates a class-wise trust score for each expert using a smoothed class-wise precision formulation. During inference, expert predictions are combined through class-wise generalized product-of-experts aggregation, allowing different experts to be emphasized for different classes. Experiments on CIFAR-100-LT, ImageNet-LT, and Places-LT across multiple backbones show that CLEAR achieves competitive overall accuracy and particularly strong few-shot performance. These results support class-wise expert reliability as a useful design principle for long-tailed ensemble learning.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-13 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.11287 — 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 2026-10-19T05:08:46.675Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-13?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).