Metraipolis › archive › dc_90c07c66fa4a
SCI-CLIP: Segment-Centric Inference with Reference Memory for Training-Free Open-Vocabulary Segmentation — arXiv:2608.05627
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.05627
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T10:36:02.603Z
- SHA-256 of the archived text
8f071cb6b85284aeddc040dde37bbb574d52d4507e0dc1fb0648f5b91fa92144- Stable URL of this page
https://metraipolis.com/documento/dc_90c07c66fa4a
How to cite
SCI-CLIP: Segment-Centric Inference with Reference Memory for Training-Free Open-Vocabulary Segmentation — arXiv:2608.05627 — arXiv (en), https://arxiv.org/abs/2608.05627 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_90c07c66fa4a (Metraipolis archive dc_90c07c66fa4a, sha256 8f071cb6b85284aeddc040dde37bbb574d52d4507e0dc1fb0648f5b91fa92144)
BibTeX
@misc{dc90c07c66fa4a,
title = {SCI-CLIP: Segment-Centric Inference with Reference Memory for Training-Free Open-Vocabulary Segmentation — arXiv:2608.05627},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.05627},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_90c07c66fa4a; sha256 8f071cb6b85284aeddc040dde37bbb574d52d4507e0dc1fb0648f5b91fa92144},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.05627. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Training-free open-vocabulary segmentation remains limited by a missing inference abstraction. Frozen vision-language features are produced at patch level, yet dense prediction requires a unit that simultaneously governs feature interaction, spatial support, contextual recovery, and retrieval-based correction. We present SCI-CLIP, a segment-centric inference framework built around the principle that the same region abstraction should organize all stages of dense open-vocabulary prediction. SCI-CLIP first induces a region-consistent interaction graph over frozen visual tokens, then reconstructs dense features by propagating values over this graph, augmenting them with selective cross-window support only where local evidence is insufficient. The same segment abstraction is subsequently used to construct and query an offline reference memory, aligning exemplar retrieval with the units on which prediction is made. SCI-CLIP turns frozen CLIP-style features into spatially coherent, context-aware, and retrieval-compatible dense predictions without any training. SCI-CLIP consistently improves the structural quality of dense predictions, the robustness of contextual reasoning, and the alignment of exemplar-based correction, yielding stronger open-vocabulary segmentation across eight benchmarks. Project code is available at: this https URL . Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-07 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.05627 — 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 2026-10-31T10:23:30.989Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).