{"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/efficient-rgb-t-tracking-via-cross-modality","title":"Efficient RGB-T Tracking via Cross-Modality Distillation","arxiv_id":null,"date":"2023-01-01","proceeding":"CVPR 2023 1","authors":["Tianlu Zhang","Hongyuan Guo","Qiang Jiao","Qiang Zhang","Jungong Han"],"abstract":"    Most current RGB-T trackers adopt a two-stream structure to extract unimodal RGB and thermal features and complex fusion strategies to achieve multi-modal feature fusion, which require a huge number of parameters, thus hindering their real-life applications. On the other hand, a compact RGB-T tracker may be computationally efficient but encounter non-negligible performance degradation, due to the weakening of feature representation ability. To remedy this situation, a cross-modality distillation framework is presented to bridge the performance gap between a compact tracker and a powerful tracker. Specifically, a specific-common feature distillation module is proposed to transform the modality-common information as well as the modality-specific information from a deeper two-stream network to a shallower single-stream network. In addition, a multi-path selection distillation module is proposed to instruct a simple fusion module to learn more accurate multi-modal information from a well-designed fusion mechanism by using multiple paths. We validate the effectiveness of our method with extensive experiments on three RGB-T benchmarks, which achieves state-of-the-art performance but consumes much less computational resources.    ","url_abs":"http://openaccess.thecvf.com//content/CVPR2023/html/Zhang_Efficient_RGB-T_Tracking_via_Cross-Modality_Distillation_CVPR_2023_paper.html","url_pdf":"http://openaccess.thecvf.com//content/CVPR2023/papers/Zhang_Efficient_RGB-T_Tracking_via_Cross-Modality_Distillation_CVPR_2023_paper.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":[],"tasks":[{"task_slug":"rgb-t-tracking","task_name":"Rgb-T Tracking"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/rgb-t-tracking-on-gtot","task":"Rgb-T Tracking","dataset":"GTOT","model":"CMD","rank_in_archive_order":12,"of":15,"metrics":{"Precision":"89.2","Success":"73.4"},"uses_additional_data":false},{"leaderboard":"/sota/rgb-t-tracking-on-lasher","task":"Rgb-T Tracking","dataset":"LasHeR","model":"CMD","rank_in_archive_order":33,"of":39,"metrics":{"Precision":"59.0","Success":"46.6"},"uses_additional_data":false},{"leaderboard":"/sota/rgb-t-tracking-on-rgbt234","task":"Rgb-T Tracking","dataset":"RGBT234","model":"CMD","rank_in_archive_order":35,"of":42,"metrics":{"Precision":"82.4","Success":"58.4"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}