Metraipolis › archive › dc_93a4bb71bb83

MESAM: Enhancing SAM2 for Few-Shot Segmentation through Semantic-Visual Memory Generation and Refinement — arXiv:2611.08943

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.08943
License (as archived): CC0-1.0
Archived: 2026-11-09T22:45:10.707Z
SHA-256 of the archived text: 371e6559446c9625ebd0d716b1f04059ea2d55b520b3d104f064986962a8484d
Stable URL of this page: https://metraipolis.com/documento/dc_93a4bb71bb83

How to cite

MESAM: Enhancing SAM2 for Few-Shot Segmentation through Semantic-Visual Memory Generation and Refinement — arXiv:2611.08943 — arXiv (en), https://arxiv.org/abs/2611.08943 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_93a4bb71bb83 (Metraipolis archive dc_93a4bb71bb83, sha256 371e6559446c9625ebd0d716b1f04059ea2d55b520b3d104f064986962a8484d)

BibTeX

@misc{dc93a4bb71bb83,
  title = {MESAM: Enhancing SAM2 for Few-Shot Segmentation through Semantic-Visual Memory Generation and Refinement — arXiv:2611.08943},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.08943},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_93a4bb71bb83; sha256 371e6559446c9625ebd0d716b1f04059ea2d55b520b3d104f064986962a8484d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.08943. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

This paper investigates how to leverage the powerful capabilities of the Segment Anything Model 2 (SAM2) to tackle few-shot segmentation (FSS) tasks. One major challenge lies in the substantial appearance differences between the support and query images, which may diminish the effectiveness of the memory-matching process in SAM2. Through systematic analysis, we find that the memory generated based on the categorical semantic information is robust to this appearance divergence and is more compatible with SAM2. Based on these observations, we propose a new Memory-Enhanced SAM2 (MESAM) method, which first introduces a Semantic-Visual Memory Generation (SVMG) module to separately construct a query semantic memory, a query foreground visual memory, and a support adaptive visual memory. Then, in our designed Interactive Semantic Memory Refinement (ISMR) module, we further enrich the obtained semantic memory with fine-grained visual details, and suppress its misatcivated background responses. Extensive experiments on the PASCAL-$5^i$, COCO-$20^i$, and LVIS-$92^i$ datasets demonstrate that MESAM consistently outperforms existing FSS methods, achieving new state-of-the-art segmentation performance. Our source code is available at: \href{ this https URL }{ this https URL }.

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/2611.08943 — 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 2026-11-09T22:37:47.213Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).