{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/sansa-unleashing-the-hidden-semantics-in-sam2","title":"SANSA: Unleashing the Hidden Semantics in SAM2 for Few-Shot Segmentation","arxiv_id":"2505.21795","date":"2025-05-27","proceeding":null,"authors":["Claudia Cuttano","Gabriele Trivigno","Giuseppe Averta","Carlo Masone"],"abstract":"Few-shot segmentation aims to segment unseen object categories from just a handful of annotated examples. This requires mechanisms that can both identify semantically related objects across images and accurately produce segmentation masks. We note that Segment Anything 2 (SAM2), with its prompt-and-propagate mechanism, offers both strong segmentation capabilities and a built-in feature matching process. However, we show that its representations are entangled with task-specific cues optimized for object tracking, which impairs its use for tasks requiring higher level semantic understanding. Our key insight is that, despite its class-agnostic pretraining, SAM2 already encodes rich semantic structure in its features. We propose SANSA (Semantically AligNed Segment Anything 2), a framework that makes this latent structure explicit, and repurposes SAM2 for few-shot segmentation through minimal task-specific modifications. SANSA achieves state-of-the-art performance on few-shot segmentation benchmarks specifically designed to assess generalization, outperforms generalist methods in the popular in-context setting, supports various prompts flexible interaction via points, boxes, or scribbles, and remains significantly faster and more compact than prior approaches. Code is available at https://github.com/ClaudiaCuttano/SANSA.","url_abs":"https://arxiv.org/abs/2505.21795v1","url_pdf":"https://arxiv.org/pdf/2505.21795v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"sansa-unleashing-the-hidden-semantics-in-sam2","repo_url":"https://github.com/claudiacuttano/sansa","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"object-tracking","task_name":"Object Tracking"},{"task_slug":"segmentation","task_name":"Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2505.21795","atlas_url":"https://app.syntology.ai/?focus=2505.21795","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.21795"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/ClaudiaCuttano/SANSA","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/claudiacuttano/sansa","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":2},"by_repo_kind":{"official":{"samples":2,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"9f2171cc1758c725","entry":"format_prompt","repo":"ClaudiaCuttano/SANSA","repo_kind":"official","path":"util/demo_sansa.py","file_url":"https://github.com/ClaudiaCuttano/SANSA/blob/HEAD/util/demo_sansa.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9f2171cc1758c725"}},{"code_sha256_prefix":"b80dba415864bb6d","entry":"generate_scribble","repo":"ClaudiaCuttano/SANSA","repo_kind":"official","path":"util/demo_sansa.py","file_url":"https://github.com/ClaudiaCuttano/SANSA/blob/HEAD/util/demo_sansa.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b80dba415864bb6d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}