{"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/simltd-simple-supervised-and-semi-supervised","title":"SimLTD: Simple Supervised and Semi-Supervised Long-Tailed Object Detection","arxiv_id":"2412.20047","date":"2024-12-28","proceeding":"CVPR 2025 1","authors":["Phi Vu Tran"],"abstract":"Recent years have witnessed tremendous advances on modern visual recognition systems. Despite such progress, many vision models still struggle with the open problem of learning from few exemplars. This paper focuses on the task of object detection in the setting where object classes follow a natural long-tailed distribution. Existing approaches to long-tailed detection resort to external ImageNet labels to augment the low-shot training instances. However, such dependency on a large labeled database is impractical and has limited utility in realistic scenarios. We propose a more versatile approach to leverage optional unlabeled images, which are easy to collect without the burden of human annotations. Our SimLTD framework is straightforward and intuitive, and consists of three simple steps: (1) pre-training on abundant head classes; (2) transfer learning on scarce tail classes; and (3) fine-tuning on a sampled set of both head and tail classes. Our approach can be viewed as an improved head-to-tail model transfer paradigm without the added complexities of meta-learning or knowledge distillation, as was required in past research. By harnessing supplementary unlabeled images, without extra image labels, SimLTD establishes new record results on the challenging LVIS v1 benchmark across both supervised and semi-supervised settings.","url_abs":"https://arxiv.org/abs/2412.20047v1","url_pdf":"https://arxiv.org/pdf/2412.20047v1.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":"simltd-simple-supervised-and-semi-supervised","repo_url":"https://github.com/lexisnexis-risk-open-source/simltd","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"few-shot-object-detection","task_name":"Few-Shot Object Detection"},{"task_slug":"long-tailed-object-detection","task_name":"Long-tailed Object Detection"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"semi-supervised-object-detection","task_name":"Semi-Supervised Object Detection"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[{"method_slug":"dino","method_name":"DINO"},{"method_slug":"deformable-detr","method_name":"Deformable DETR"},{"method_slug":"faster-r-cnn","method_name":"Faster R-CNN"},{"method_slug":"rpn","method_name":"RPN"},{"method_slug":"swin-transformer","method_name":"Swin Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/object-detection-on-lvis-v1-0-val","task":"Object Detection","dataset":"LVIS v1.0 val","model":"SimLTD w/MixPL (Swin-L + COCO unlabeled images)","rank_in_archive_order":8,"of":15,"metrics":{"box AP":"51.5"},"uses_additional_data":true},{"leaderboard":"/sota/object-detection-on-lvis-v1-0-val","task":"Object Detection","dataset":"LVIS v1.0 val","model":"SimLTD Fully Supervised (Swin-L)","rank_in_archive_order":12,"of":15,"metrics":{"box AP":"49.8","box APr":"42.4"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}