{"paper":{"title":"On Efficient Variants of Segment Anything Model: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"This survey reviews acceleration strategies for the Segment Anything Model and benchmarks their efficiency-accuracy trade-offs on multiple hardware platforms.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Heng Tao Shen, Jun Liu, Ping Hu, Xiaofeng Zhu, Xiaorui Sun","submitted_at":"2024-10-07T11:59:54Z","abstract_excerpt":"The Segment Anything Model (SAM) is a foundational model for image segmentation tasks, known for its strong generalization across diverse applications. However, its impressive performance comes with significant computational and resource demands, making it challenging to deploy in resource-limited environments such as edge devices. To address this, a variety of SAM variants have been proposed to enhance efficiency while keeping accuracy. This survey provides the first comprehensive review of these efficient SAM variants. We begin by exploring the motivations driving this research. We then pres"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"This survey provides the first comprehensive review of efficient SAM variants. We begin by exploring the motivations driving this research. We then present core techniques used in SAM and model acceleration. This is followed by a detailed exploration of SAM acceleration strategies, categorized by approach, and a discussion of several future research directions. Finally, we offer a unified and extensive evaluation of these methods across various hardware, assessing their efficiency and accuracy on representative benchmarks, and providing a clear comparison of their overall performance.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The review assumes that the authors have identified and fairly categorized all major efficient SAM variants without significant selection bias and that the chosen benchmarks and hardware platforms are representative of real deployment scenarios.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A survey that reviews efficient variants of the Segment Anything Model, categorizes acceleration strategies, and provides a unified hardware evaluation on benchmarks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"This survey reviews acceleration strategies for the Segment Anything Model and benchmarks their efficiency-accuracy trade-offs on multiple hardware platforms.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"8c8cf4bf6f144fed4c253c6b06862485a220547a6238a50e5059bd49bffb5589"},"source":{"id":"2410.04960","kind":"arxiv","version":6},"verdict":{"id":"4575454f-b331-4bd0-b76f-3abb6188df5d","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-23T19:40:39.357352Z","strongest_claim":"This survey provides the first comprehensive review of efficient SAM variants. We begin by exploring the motivations driving this research. We then present core techniques used in SAM and model acceleration. This is followed by a detailed exploration of SAM acceleration strategies, categorized by approach, and a discussion of several future research directions. Finally, we offer a unified and extensive evaluation of these methods across various hardware, assessing their efficiency and accuracy on representative benchmarks, and providing a clear comparison of their overall performance.","one_line_summary":"A survey that reviews efficient variants of the Segment Anything Model, categorizes acceleration strategies, and provides a unified hardware evaluation on benchmarks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The review assumes that the authors have identified and fairly categorized all major efficient SAM variants without significant selection bias and that the chosen benchmarks and hardware platforms are representative of real deployment scenarios.","pith_extraction_headline":"This survey reviews acceleration strategies for the Segment Anything Model and benchmarks their efficiency-accuracy trade-offs on multiple hardware platforms."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2410.04960/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}