{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/stitcher-feedback-driven-data-provider-for","title":"Dynamic Scale Training for Object Detection","arxiv_id":"2004.12432","date":"2020-04-26","proceeding":null,"authors":["Yukang Chen","Peizhen Zhang","Zeming Li","Yanwei Li","Xiangyu Zhang","Lu Qi","Jian Sun","Jiaya Jia"],"abstract":"We propose a Dynamic Scale Training paradigm (abbreviated as DST) to mitigate scale variation challenge in object detection. Previous strategies like image pyramid, multi-scale training, and their variants are aiming at preparing scale-invariant data for model optimization. However, the preparation procedure is unaware of the following optimization process that restricts their capability in handling the scale variation. Instead, in our paradigm, we use feedback information from the optimization process to dynamically guide the data preparation. The proposed method is surprisingly simple yet obtains significant gains (2%+ Average Precision on MS COCO dataset), outperforming previous methods. Experimental results demonstrate the efficacy of our proposed DST method towards scale variation handling. It could also generalize to various backbones, benchmarks, and other challenging downstream tasks like instance segmentation. It does not introduce inference overhead and could serve as a free lunch for general detection configurations. Besides, it also facilitates efficient training due to fast convergence. Code and models are available at github.com/yukang2017/Stitcher.","url_abs":"https://arxiv.org/abs/2004.12432v2","url_pdf":"https://arxiv.org/pdf/2004.12432v2.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":"stitcher-feedback-driven-data-provider-for","repo_url":"https://github.com/yukang2017/Stitcher","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"stitcher-feedback-driven-data-provider-for","repo_url":"https://github.com/5m0k3/gwd-efficientdet-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"stitcher-feedback-driven-data-provider-for","repo_url":"https://github.com/5m0k3/gwd-yolov5-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"stitcher-feedback-driven-data-provider-for","repo_url":"https://github.com/tanmaypandey7/wheat-detection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"model-optimization","task_name":"Model Optimization"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"dst","method_name":"DST"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2004.12432","atlas_url":"https://app.syntology.ai/?focus=2004.12432","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2004.12432"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2004.12432\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2004.12432"},"call":"get_concepts_for_paper(arxiv_id=\"2004.12432\")"}],"by_repo":[{"repo":"yukang2017/Stitcher","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"5m0k3/gwd-efficientdet-pytorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"5m0k3/gwd-yolov5-pytorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"tanmaypandey7/wheat-detection","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1710.09412"],"harvested_for_calls":[{"arxiv_id":"1710.09412","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1710.09412"},"call":"get_harvested_code_for_paper(arxiv_id=\"1710.09412\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"c12a3cfc8790aef9856b5e7d7039a5803a182a00852ca4be725deb4f099b4fe7","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}