Metraipolis › archive › dc_264bde25fc9f

ReMaD: Tuning-free Domain Adaptation for Classification and Out-of-Distribution Detection — arXiv:2610.05718

Source
arXiv
Original
https://arxiv.org/abs/2610.05718
License (as archived)
CC0-1.0
Archived
2026-10-06T05:31:13.654Z
SHA-256 of the archived text
578d5669c70d2d397204d0c91ef8a5ea46a0007e4b6064bb71a713efa9a18262
Stable URL of this page
https://metraipolis.com/documento/dc_264bde25fc9f

How to cite

ReMaD: Tuning-free Domain Adaptation for Classification and Out-of-Distribution Detection — arXiv:2610.05718 — arXiv, https://arxiv.org/abs/2610.05718 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_264bde25fc9f (Metraipolis archive dc_264bde25fc9f, sha256 578d5669c70d2d397204d0c91ef8a5ea46a0007e4b6064bb71a713efa9a18262)
BibTeX
@misc{dc264bde25fc9f,
  title = {ReMaD: Tuning-free Domain Adaptation for Classification and Out-of-Distribution Detection — arXiv:2610.05718},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.05718},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_264bde25fc9f; sha256 578d5669c70d2d397204d0c91ef8a5ea46a0007e4b6064bb71a713efa9a18262},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.05718. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We introduce Reduced-rank Mahalanobis Distance (ReMaD), a novel prototypical distance-based refinement to classification and out-of-distribution (OOD) detection using pretrained models without finetuning. We use embeddings of the target dataset to fit closed-form distribution statistics in the model's latent space which can classify in-distribution samples and detect OOD samples, all without training or prior knowledge of the OOD data. Building on prototype classification and OOD detection, we analyze the distribution properties of large pretrained models when processing new datasets; based on this analysis, we formulate a simple modification to Mahalanobis Distance to adapt models' latent space distributions to new domains by removing unused features, without the finetuning or hyperparameter searches required by other adaptation procedures. We demonstrate the efficacy of this method to adapt existing large pretrained image embedding models to new classification domains outside their trained capabilities by testing across four target datasets, with competitive performance in both classification and OOD detection.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.05718 — 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 2026-10-06T05:27:05.819Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).