{"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/sdstrack-self-distillation-symmetric-adapter","title":"SDSTrack: Self-Distillation Symmetric Adapter Learning for Multi-Modal Visual Object Tracking","arxiv_id":"2403.16002","date":"2024-03-24","proceeding":"CVPR 2024 1","authors":["Xiaojun Hou","Jiazheng Xing","Yijie Qian","Yaowei Guo","Shuo Xin","JunHao Chen","Kai Tang","Mengmeng Wang","Zhengkai Jiang","Liang Liu","Yong liu"],"abstract":"Multimodal Visual Object Tracking (VOT) has recently gained significant attention due to its robustness. Early research focused on fully fine-tuning RGB-based trackers, which was inefficient and lacked generalized representation due to the scarcity of multimodal data. Therefore, recent studies have utilized prompt tuning to transfer pre-trained RGB-based trackers to multimodal data. However, the modality gap limits pre-trained knowledge recall, and the dominance of the RGB modality persists, preventing the full utilization of information from other modalities. To address these issues, we propose a novel symmetric multimodal tracking framework called SDSTrack. We introduce lightweight adaptation for efficient fine-tuning, which directly transfers the feature extraction ability from RGB to other domains with a small number of trainable parameters and integrates multimodal features in a balanced, symmetric manner. Furthermore, we design a complementary masked patch distillation strategy to enhance the robustness of trackers in complex environments, such as extreme weather, poor imaging, and sensor failure. Extensive experiments demonstrate that SDSTrack outperforms state-of-the-art methods in various multimodal tracking scenarios, including RGB+Depth, RGB+Thermal, and RGB+Event tracking, and exhibits impressive results in extreme conditions. Our source code is available at https://github.com/hoqolo/SDSTrack.","url_abs":"https://arxiv.org/abs/2403.16002v2","url_pdf":"https://arxiv.org/pdf/2403.16002v2.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":"sdstrack-self-distillation-symmetric-adapter","repo_url":"https://github.com/hoqolo/sdstrack","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":"rgb-t-tracking","task_name":"Rgb-T Tracking"},{"task_slug":"visual-object-tracking","task_name":"Visual Object Tracking"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/rgb-t-tracking-on-lasher","task":"Rgb-T Tracking","dataset":"LasHeR","model":"SDSTrack","rank_in_archive_order":31,"of":39,"metrics":{"Precision":"66.5","Success":"53.1"},"uses_additional_data":false},{"leaderboard":"/sota/rgb-t-tracking-on-rgbt234","task":"Rgb-T Tracking","dataset":"RGBT234","model":"SDSTrack","rank_in_archive_order":30,"of":42,"metrics":{"Precision":"84.8","Success":"62.5"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2403.16002","atlas_url":"https://app.syntology.ai/?focus=2403.16002","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.16002"}},"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/hoqolo/SDSTrack","reach":null}],"summary":{"ran":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":"4e59c211afbdecef","entry":"SDSTrack","repo":"hoqolo/SDSTrack","repo_kind":"official","path":"lib/models/sdstrack/sdstrack.py","file_url":"https://github.com/hoqolo/SDSTrack/blob/HEAD/lib/models/sdstrack/sdstrack.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4e59c211afbdecef"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}