Metraipolis › archive › dc_4bd76dcce74f

Fisher Contrastive Learning to Mitigate Feature Suppression: A Case Study in Acute Promyelocytic Leukemia Diagnosis — arXiv:2610.40162

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.40162
License (as archived)
CC0-1.0
Archived
2026-11-01T02:27:20.262Z
SHA-256 of the archived text
42ef3ed3b6289a6cb794f06d113b56bbbb4ae89471d4a121bb94f7fd8594c85c
Stable URL of this page
https://metraipolis.com/documento/dc_4bd76dcce74f

How to cite

Fisher Contrastive Learning to Mitigate Feature Suppression: A Case Study in Acute Promyelocytic Leukemia Diagnosis — arXiv:2610.40162 — arXiv (en), https://arxiv.org/abs/2610.40162 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4bd76dcce74f (Metraipolis archive dc_4bd76dcce74f, sha256 42ef3ed3b6289a6cb794f06d113b56bbbb4ae89471d4a121bb94f7fd8594c85c)
BibTeX
@misc{dc4bd76dcce74f,
  title = {Fisher Contrastive Learning to Mitigate Feature Suppression: A Case Study in Acute Promyelocytic Leukemia Diagnosis — arXiv:2610.40162},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.40162},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4bd76dcce74f; sha256 42ef3ed3b6289a6cb794f06d113b56bbbb4ae89471d4a121bb94f7fd8594c85c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.40162. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Self-supervised contrastive learning (SSCL) learns representations by contrasting augmented views of the same sample, but it can exhibit feature suppression, where dominant or easy-to-learn factors suppress other class-relevant signals, degrading the performance of representations, particularly in high-dimensional data with heterogeneous features. We introduce Fisher Contrastive Learning (FCL), which uses a regularized Fisher trace criterion to address feature suppression. FCL learns embeddings by maximizing the discriminative strength of Fisher discriminant functions, producing representations that preserve class-relevant information implied by the augmentation process. We prove that the representations learned by FCL could alleviate the feature suppression effects. We demonstrate FCL on simulated benchmarks designed to induce feature suppression and on a real-world biomedical application, pretraining on large white blood cell microscopy image dataset and transfer learning for diagnosis of acute promyelocytic leukemia in an external cohort. In all experiments, FCL outperforms the self-supervised baselines and yields more robust and discriminative representations.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.40162 — 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 2026-11-01T02:12:44.319Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).