Metraipolis › archive › dc_b9aff238c031
Complementing DINO Features with Image Structure for Part Discovery — arXiv:2610.32293
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.32293
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-26T19:51:52.233Z
- SHA-256 of the archived text
03258832ce591e53f739c0ff0fc288238ee9efb00c57a12a64d5b904afb108d3- Stable URL of this page
https://metraipolis.com/documento/dc_b9aff238c031
How to cite
Complementing DINO Features with Image Structure for Part Discovery — arXiv:2610.32293 — arXiv (en), https://arxiv.org/abs/2610.32293 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b9aff238c031 (Metraipolis archive dc_b9aff238c031, sha256 03258832ce591e53f739c0ff0fc288238ee9efb00c57a12a64d5b904afb108d3)
BibTeX
@misc{dcb9aff238c031,
title = {Complementing DINO Features with Image Structure for Part Discovery — arXiv:2610.32293},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.32293},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b9aff238c031; sha256 03258832ce591e53f739c0ff0fc288238ee9efb00c57a12a64d5b904afb108d3},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.32293. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Self-supervised Vision Transformers (ViTs) like DINO encode rich semantics, enabling training-free segmentation of objects from the background and discovery of their parts via feature clustering. This paper focuses on part discovery: partitioning a foreground object into semantic parts. Existing approaches produce imprecise part boundaries. We trace this to the rigid ViT patch grid used in training DINO, where patches straddling boundaries contain pixels from multiple parts. While DINO's invariance-based training could absorb this pixel-level mixing into clean features, experiments with over 26K foreground patches show it does not: boundary-overlapping patches produce features with higher entropy and lower assignment confidence, blurring predicted part boundaries. Rather than make the massive effort of retraining DINO over geometrically coherent regions, an easier approach is to take boundaries directly from a boundary detector, which supplies the geometric information DINO's features lack. Motivated by this, we introduce Part-DINO, a training-free framework that combines boundaries from low-level image segmentation with DINO's semantic features. We use the boundaries to partition the image into regions, pool DINO features within each region, and group them to discover parts. Without any training, Part-DINO produces structurally coherent part assignments, outperforming training-free baselines across four standard benchmarks (CUB, CelebA, PartImageNet-OOD, PartImageNet-Seg) and remaining competitive with weakly-supervised and unsupervised methods. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.32293 — 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 2026-10-26T19:45:33.406Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).