{"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/integral-migrating-pre-trained-transformer","title":"Integrally Migrating Pre-trained Transformer Encoder-decoders for Visual Object Detection","arxiv_id":"2205.09613","date":"2022-05-19","proceeding":"ICCV 2023 1","authors":["Feng Liu","Xiaosong Zhang","Zhiliang Peng","Zonghao Guo","Fang Wan","Xiangyang Ji","Qixiang Ye"],"abstract":"Modern object detectors have taken the advantages of backbone networks pre-trained on large scale datasets. Except for the backbone networks, however, other components such as the detector head and the feature pyramid network (FPN) remain trained from scratch, which hinders fully tapping the potential of representation models. In this study, we propose to integrally migrate pre-trained transformer encoder-decoders (imTED) to a detector, constructing a feature extraction path which is ``fully pre-trained\" so that detectors' generalization capacity is maximized. The essential differences between imTED with the baseline detector are twofold: (1) migrating the pre-trained transformer decoder to the detector head while removing the randomly initialized FPN from the feature extraction path; and (2) defining a multi-scale feature modulator (MFM) to enhance scale adaptability. Such designs not only reduce randomly initialized parameters significantly but also unify detector training with representation learning intendedly. Experiments on the MS COCO object detection dataset show that imTED consistently outperforms its counterparts by $\\sim$2.4 AP. Without bells and whistles, imTED improves the state-of-the-art of few-shot object detection by up to 7.6 AP. Code is available at https://github.com/LiewFeng/imTED.","url_abs":"https://arxiv.org/abs/2205.09613v2","url_pdf":"https://arxiv.org/pdf/2205.09613v2.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":"integral-migrating-pre-trained-transformer","repo_url":"https://github.com/liewfeng/imted","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"integral-migrating-pre-trained-transformer","repo_url":"https://github.com/bohao-lee/pdc","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"integral-migrating-pre-trained-transformer","repo_url":"https://github.com/yuhongtian17/spatial-transform-decoupling","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"few-shot-object-detection","task_name":"Few-Shot Object Detection"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"fpn","method_name":"FPN"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/few-shot-object-detection-on-ms-coco-10-shot","task":"Few-Shot Object Detection","dataset":"MS-COCO (10-shot)","model":"imTED+ViT-B","rank_in_archive_order":7,"of":33,"metrics":{"AP":"22.5"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-object-detection-on-ms-coco-10-shot","task":"Few-Shot Object Detection","dataset":"MS-COCO (10-shot)","model":"imTED+ViT-S","rank_in_archive_order":18,"of":33,"metrics":{"AP":"15.0"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-object-detection-on-ms-coco-30-shot","task":"Few-Shot Object Detection","dataset":"MS-COCO (30-shot)","model":"imTED+ViT-B","rank_in_archive_order":6,"of":25,"metrics":{"AP":"30.2"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-object-detection-on-ms-coco-30-shot","task":"Few-Shot Object Detection","dataset":"MS-COCO (30-shot)","model":"imTED+ViT-S","rank_in_archive_order":14,"of":25,"metrics":{"AP":"21.0"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2205.09613","atlas_url":"https://app.syntology.ai/?focus=2205.09613","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":"2205.09613"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2205.09613\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2205.09613"},"call":"get_concepts_for_paper(arxiv_id=\"2205.09613\")"}],"by_repo":[{"repo":"liewfeng/imted","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["Liu_Integrally_Migrating_Pre-trained_Transformer_Encoder-decoders_for_Visual_Object_Detection_ICCV_2023_paper"],"harvested_for_calls":[]},{"repo":"bohao-lee/pdc","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2007.09384"],"harvested_for_calls":[{"arxiv_id":"2007.09384","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2007.09384"},"call":"get_harvested_code_for_paper(arxiv_id=\"2007.09384\")"}]},{"repo":"yuhongtian17/spatial-transform-decoupling","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["aaai_28502"],"harvested_for_calls":[]}],"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":"e684ec65fe52a8cae2233db6bc4f6158954158dc9ab194e78b37f036ce379709","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}