Metraipolis › archive › dc_ce6892deff70

Fi-ImageNet-1k: An OOD Benchmark From the Inside of the ImageNet-1k Validation Set — arXiv:2609.01027

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.01027
License (as archived)
CC0-1.0
Archived
2026-10-17T07:13:46.739Z
SHA-256 of the archived text
690fa1bea46b190735164bb71d5c3137c16bd26789d681a13fe249a045600abc
Stable URL of this page
https://metraipolis.com/documento/dc_ce6892deff70

How to cite

Fi-ImageNet-1k: An OOD Benchmark From the Inside of the ImageNet-1k Validation Set — arXiv:2609.01027 — arXiv (en), https://arxiv.org/abs/2609.01027 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ce6892deff70 (Metraipolis archive dc_ce6892deff70, sha256 690fa1bea46b190735164bb71d5c3137c16bd26789d681a13fe249a045600abc)
BibTeX
@misc{dcce6892deff70,
  title = {Fi-ImageNet-1k: An OOD Benchmark From the Inside of the ImageNet-1k Validation Set — arXiv:2609.01027},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.01027},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ce6892deff70; sha256 690fa1bea46b190735164bb71d5c3137c16bd26789d681a13fe249a045600abc},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.01027. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Out-of-distribution (OOD) detection predicts whether a test image belongs to none of the predefined classes. To evaluate this task, benchmarks need images from outside the in-distribution (ID) data; typically, these are defined or collected in an ad hoc fashion. Since no ground truth is perfect, ID-labeled datasets themselves contain a natural source of OOD images. We exploit such annotation errors and present Fi-ImageNet-1k, an OOD dataset built from ImageNet-1k validation images that the recent ReImageNet reannotation effort assigned to no ImageNet-1k class. Each image was examined by expert human annotators supported by evidence from MLLMs, VLMs, and reverse image search, comparing it against all visually similar ID classes. We keep only images that could be assigned a specific class outside the ImageNet-1k label space. The resulting Fi-ImageNet-1k, with 655 images from 522 classes, is substantially more challenging than any commonly used OOD dataset. No evaluated combination of classifier and OOD detector achieves a false positive rate below 51% at 95% true positive rate (FPR@95). Compared to the recent NINCO, our dataset is 3.8x more challenging in the FPR@95 metric for state-of-the-art supervised OOD detection methods.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-02 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.01027 — 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 2026-10-17T07:00:58.961Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).