Metraipolis › archive › dc_6e827fa59be8
Beyond Resolution: Object-to-Image Ratio Mismatch in Instance Retrieval — arXiv:2610.11489
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.11489
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T06:30:07.098Z
- SHA-256 of the archived text
d25d4b780ea56a61014cb468d13268a28b0c6ddea4c44bc144046e16aabb2289- Stable URL of this page
https://metraipolis.com/documento/dc_6e827fa59be8
How to cite
Beyond Resolution: Object-to-Image Ratio Mismatch in Instance Retrieval — arXiv:2610.11489 — arXiv (en), https://arxiv.org/abs/2610.11489 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6e827fa59be8 (Metraipolis archive dc_6e827fa59be8, sha256 d25d4b780ea56a61014cb468d13268a28b0c6ddea4c44bc144046e16aabb2289)
BibTeX
@misc{dc6e827fa59be8,
title = {Beyond Resolution: Object-to-Image Ratio Mismatch in Instance Retrieval — arXiv:2610.11489},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.11489},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6e827fa59be8; sha256 d25d4b780ea56a61014cb468d13268a28b0c6ddea4c44bc144046e16aabb2289},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.11489. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Visual instance retrieval often fails when the same object appears at different apparent sizes in the query and gallery. We show that the dominant cause is usually not resolution loss but object-to-image (O2I) ratio mismatch: the object occupies different fractions of the two images. On a controlled benchmark of 3,021 Objaverse objects rendered at five camera distances, more than 80% of the cross-distance degradation is attributable to O2I mismatch rather than resolution for 9 of 12 pretrained backbones; multi-scale architectures cut the resolution-only effect to single digits yet remain equally susceptible. The failure is also asymmetric: tight queries retrieve more reliably against wide gallery images than the reverse. Guided by this analysis, query-side scale augmentation and an OWLv2 crop reranker reach state of the art on ILIAS 100M (29.2 mAP@1000 before reranking, 42.0 after) without training or modifying the precomputed gallery index, and a LoRA fine-tune matches the query-side gains at a single forward pass, showing that O2I robustness is learnable. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.IR, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Information Retrieval (cs.IR). Pagina del lavoro: https://arxiv.org/abs/2610.11489 — 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 2026-10-09T05:54:51.514Z dalla pagina https://arxiv.org/list/cs.IR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).