{"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/samurai-adapting-segment-anything-model-for-1","title":"SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory","arxiv_id":"2411.11922","date":"2024-11-18","proceeding":null,"authors":["Cheng-Yen Yang","Hsiang-Wei Huang","Wenhao Chai","Zhongyu Jiang","Jenq-Neng Hwang"],"abstract":"The Segment Anything Model 2 (SAM 2) has demonstrated strong performance in object segmentation tasks but faces challenges in visual object tracking, particularly when managing crowded scenes with fast-moving or self-occluding objects. Furthermore, the fixed-window memory approach in the original model does not consider the quality of memories selected to condition the image features for the next frame, leading to error propagation in videos. This paper introduces SAMURAI, an enhanced adaptation of SAM 2 specifically designed for visual object tracking. By incorporating temporal motion cues with the proposed motion-aware memory selection mechanism, SAMURAI effectively predicts object motion and refines mask selection, achieving robust, accurate tracking without the need for retraining or fine-tuning. SAMURAI operates in real-time and demonstrates strong zero-shot performance across diverse benchmark datasets, showcasing its ability to generalize without fine-tuning. In evaluations, SAMURAI achieves significant improvements in success rate and precision over existing trackers, with a 7.1% AUC gain on LaSOT$_{\\text{ext}}$ and a 3.5% AO gain on GOT-10k. Moreover, it achieves competitive results compared to fully supervised methods on LaSOT, underscoring its robustness in complex tracking scenarios and its potential for real-world applications in dynamic environments.","url_abs":"https://arxiv.org/abs/2411.11922v2","url_pdf":"https://arxiv.org/pdf/2411.11922v2.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":"samurai-adapting-segment-anything-model-for-1","repo_url":"https://github.com/yangchris11/samurai","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"object-tracking","task_name":"Object Tracking"},{"task_slug":"visual-object-tracking","task_name":"Visual Object Tracking"},{"task_slug":"visual-tracking","task_name":"Visual Tracking"}],"methods":[{"method_slug":"sam","method_name":"SAM"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/visual-object-tracking-on-didi","task":"Visual Object Tracking","dataset":"DiDi","model":"SAMURAI","rank_in_archive_order":2,"of":11,"metrics":{"Tracking quality":"0.680"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-got-10k","task":"Visual Object Tracking","dataset":"GOT-10k","model":"SAMURAI-L","rank_in_archive_order":1,"of":42,"metrics":{"Average Overlap":"81.7","Success Rate 0.5":"92.2","Success Rate 0.75":"76.9"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-lasot","task":"Visual Object Tracking","dataset":"LaSOT","model":"SAMURAI-L","rank_in_archive_order":10,"of":46,"metrics":{"AUC":"74.2","Normalized Precision":"82.7","Precision":"80.2"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-lasot-ext","task":"Visual Object Tracking","dataset":"LaSOT-ext","model":"SAMURAI-L","rank_in_archive_order":1,"of":18,"metrics":{"AUC":"61.0","Normalized Precision":"73.9","Precision":"72.2"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-needforspeed","task":"Visual Object Tracking","dataset":"NeedForSpeed","model":"SAMURAI-L","rank_in_archive_order":1,"of":10,"metrics":{"AUC":"0.692"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-otb-2015","task":"Visual Object Tracking","dataset":"OTB-2015","model":"SAMURAI-L","rank_in_archive_order":5,"of":18,"metrics":{"AUC":"0.715"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-trackingnet","task":"Visual Object Tracking","dataset":"TrackingNet","model":"SAMURAI-L","rank_in_archive_order":14,"of":40,"metrics":{"Accuracy":"85.3"},"uses_additional_data":false},{"leaderboard":"/sota/zero-shot-single-object-tracking-on-lasot","task":"Zero-Shot Single Object Tracking","dataset":"LaSOT","model":"SAMURAI-L","rank_in_archive_order":1,"of":2,"metrics":{"AUC":"74.2","Normalized Precision":"82.7","Precision":"80.2"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2411.11922","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.11922"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yangchris11/samurai","reach":null}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"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":"fc2fcc0303a921c0","entry":"load_lasot_gt","repo":"yangchris11/samurai","repo_kind":"official","path":"scripts/main_inference.py","file_url":"https://github.com/yangchris11/samurai/blob/HEAD/scripts/main_inference.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fc2fcc0303a921c0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}