Metraipolis › archive › dc_11ad4e0be70e

Déjà Vu: Cycle-Consistent Re-ranking for Semantic Correspondence — arXiv:2611.00328

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.00328
License (as archived)
CC0-1.0
Archived
2026-11-03T11:40:36.609Z
SHA-256 of the archived text
174292a5f8a3c507cb7555ecb3144393948fb73fc66859616ee615404b4bf581
Stable URL of this page
https://metraipolis.com/documento/dc_11ad4e0be70e

How to cite

Déjà Vu: Cycle-Consistent Re-ranking for Semantic Correspondence — arXiv:2611.00328 — arXiv (en), https://arxiv.org/abs/2611.00328 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_11ad4e0be70e (Metraipolis archive dc_11ad4e0be70e, sha256 174292a5f8a3c507cb7555ecb3144393948fb73fc66859616ee615404b4bf581)
BibTeX
@misc{dc11ad4e0be70e,
  title = {Déjà Vu: Cycle-Consistent Re-ranking for Semantic Correspondence — arXiv:2611.00328},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00328},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_11ad4e0be70e; sha256 174292a5f8a3c507cb7555ecb3144393948fb73fc66859616ee615404b4bf581},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00328. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We propose \emph{Déjà Vu}, a test-time decoding module for semantic correspondence. Matching semantically equivalent keypoints across images of the same object category is challenging due to variations in appearance, viewpoint, and scale. While features from large pretrained vision models carry strong zero-shot correspondence ability, existing methods reduce final matching to greedy top-$1$ nearest-neighbor selection. We show that the correct correspondence appears among the top-ranked candidates far more often than top-$1$ matching achieves: with $30$ candidates, zero-shot features exceed the top-$1$ accuracy of a supervised model. This reveals a \textit{decoding bottleneck} rather than a limit of the representation. Motivated by this observation, we formulate semantic correspondence as a \textit{recall-then-rerank} problem. Our method first nominates an adaptive candidate set, larger when the similarity distribution is ambiguous and smaller when it is confident, then re-ranks the candidates with a graded cycle-consistency score: each candidate is matched back to the source image and penalized by how far its reverse match lands from the original keypoint. The module operates entirely on the similarity matrix already computed by the base method. It consistently improves three representative baselines on SPair-71k, its geometric subset, and PF-Pascal under both unsupervised and weakly supervised settings, with gains of up to $+1.8$ [email protected] on SPair-71k and $+3.4$ [email protected] on PF-Pascal, and $+4.9$ under Keypoint Average Precision.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2611.00328 — 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 2026-11-03T11:06:37.415Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).