Metraipolis › archive › dc_1136744ebcac

SeCo-SBIR: Semantically Consistent Prompt Learning for Zero-Shot Sketch-Based Image Retrieval — arXiv:2608.03120

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.03120
License (as archived)
CC0-1.0
Archived
2026-10-31T12:58:15.314Z
SHA-256 of the archived text
a3579a7f5741ee34dc6b44e2cda1124636f4e4464b91ee7ffdaac6bfeed9409c
Stable URL of this page
https://metraipolis.com/documento/dc_1136744ebcac

How to cite

SeCo-SBIR: Semantically Consistent Prompt Learning for Zero-Shot Sketch-Based Image Retrieval — arXiv:2608.03120 — arXiv (en), https://arxiv.org/abs/2608.03120 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1136744ebcac (Metraipolis archive dc_1136744ebcac, sha256 a3579a7f5741ee34dc6b44e2cda1124636f4e4464b91ee7ffdaac6bfeed9409c)
BibTeX
@misc{dc1136744ebcac,
  title = {SeCo-SBIR: Semantically Consistent Prompt Learning for Zero-Shot Sketch-Based Image Retrieval — arXiv:2608.03120},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.03120},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1136744ebcac; sha256 a3579a7f5741ee34dc6b44e2cda1124636f4e4464b91ee7ffdaac6bfeed9409c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.03120. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Adapting CLIP for zero-shot sketch-based image retrieval (ZS-SBIR) via prompt learning faces a fundamental tension: the model must bridge the sketch-photo domain gap through task-specific adaptation, yet the added flexibility risks overfitting to seen training categories and eroding CLIP's zero-shot generalization. We present SeCo-SBIR, a semantically consistent prompt learning framework that resolves this tension from both sides. First, a text-guided multi-modal prompting strategy routes learnable prompt vectors through CLIP's text encoder and projects the resulting intermediate representations into the visual encoder at every layer via learnable coupling functions. Because the text encoder has already learned robust, abstract category-level semantics from large-scale language supervision, this mechanism injects transferable semantic knowledge directly into the visual pathway - adapting the model to the sketch-photo domain while inherently favoring generalization to unseen classes. Second, a perturbation-based consistency constraint addresses the residual overfitting risk from the learnable coupling functions by aligning the adapted model with a frozen CLIP reference branch using an asymmetric InfoNCE objective - augmented inputs feed the frozen branch while clean inputs feed the trainable branch - anchoring the learned representations to CLIP's generalizable feature space. Together with lightweight adapters and a multi-objective loss combining triplet, NT-Xent, and classification terms, SeCo-SBIR achieves state-of-the-art results on all three standard ZS-SBIR benchmarks across categorical, generalized, and across-dataset settings.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-05 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.03120 — 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 2026-10-31T12:45:33.224Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).