{"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":"/method/dynamic-r-cnn","slug":"dynamic-r-cnn","name":"Dynamic R-CNN","full_name":"Dynamic R-CNN","full_name_withheld":false,"description_markdown":"**Dynamic R-CNN** is an object detection method that adjusts the label assignment criteria (IoU threshold) and the shape of regression loss function (parameters of Smooth L1 Loss) automatically based on the statistics of proposals during training. The motivation is that in previous two-stage object detectors, there is an inconsistency problem between the fixed network settings and the dynamic training procedure. For example, the fixed label assignment strategy and regression loss function cannot fit the distribution change of proposals and thus are harmful to training high quality detectors.\r\n\r\nIt consists of two components: Dynamic Label Assignment and Dynamic Smooth L1 Loss, which are designed for the classification and regression branches, respectively. \r\n\r\nFor Dynamic Label Assignment, we want our model to be discriminative for high IoU proposals, so we gradually adjust the IoU threshold for positive/negative samples based on the proposals distribution in the training procedure. Specifically, we set the threshold as the IoU of the proposal at a certain percentage since it can reflect the quality of the overall distribution. \r\n\r\nFor Dynamic Smooth L1 Loss, we want to change the shape of the regression loss function to adaptively fit the distribution change of error and ensure the contribution of high quality samples to training. This is achieved by adjusting the $\\beta$ in Smooth L1 Loss based on the error distribution of the regression loss function, in which $\\beta$ actually controls the magnitude of the gradient of small errors.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training","paper":"/paper/dynamic-r-cnn-towards-high-quality-object","first_author":"Hongkai Zhang","n_authors":5,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/dynamic-r-cnn-towards-high-quality-object"},"source":{"url":"https://arxiv.org/abs/2004.06002v2","title":"Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/hkzhang95/DynamicRCNN","code_snippet_url_on_a_code_host":true,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Object Detection Models","url":"/methods/category/object-detection-models","pwc_aliases":[]}],"n_papers_tagged":3,"archive_num_papers":3,"papers_newest_first":[{"paper":null,"slug":"enhancing-tree-type-detection-in-forest-fire","title":"Enhancing Tree Type Detection in Forest Fire Risk Assessment: Multi-Stage Approach and Color Encoding with Forest Fire Risk Evaluation Framework for UAV Imagery","date":"2024-07-27","arxiv_id":"2407.19184","n_code_links":0,"syntology":null},{"paper":null,"slug":"fracture-detection-in-wrist-x-ray-images","title":"Fracture Detection in Wrist X-ray Images Using Deep Learning-Based Object Detection Models","date":"2021-11-14","arxiv_id":"2111.07355","n_code_links":0,"syntology":null},{"paper":"/paper/dynamic-r-cnn-towards-high-quality-object","slug":"dynamic-r-cnn-towards-high-quality-object","title":"Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training","date":"2020-04-13","arxiv_id":"2004.06002","n_code_links":3,"syntology":{"ran":9,"of":18,"n_ran_checked":9,"n_instrument":0,"unverified":9,"pointer_only":1,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 1 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified","official":{"repos":["hkzhang95/DynamicRCNN"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["listed","official"]}}}],"papers_shown":3,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":3,"with_a_code_link":1,"where_syntology_ran_a_sample":1,"not_listed_spam_title":0,"listed":3,"listed_where_code_ran":1,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":1,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"papers_where_code_ran":1,"papers_where_code_ran_first_page":"/method/dynamic-r-cnn/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"ran","page":1,"of":1,"url":"/method/dynamic-r-cnn/papers/ran/1","json":"/method/dynamic-r-cnn/papers/ran/1.json","rows":1}],"tasks":[{"task":"/task/object-detection","name":"Object Detection","papers":3},{"task":"/task/object-detection-1","name":"object-detection","papers":3},{"task":"/task/ensemble-learning","name":"Ensemble Learning","papers":1},{"task":"/task/fire-detection","name":"Fire Detection","papers":1},{"task":"/task/fracture-detection","name":"Fracture detection","papers":1},{"task":"/task/management","name":"Management","papers":1},{"task":"/task/medical-object-detection","name":"Medical Object Detection","papers":1},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":1},{"task":"/task/high","name":"Vocal Bursts Intensity Prediction","papers":1},{"task":"/task/regression-1","name":"regression","papers":1}],"tasks_shown":10,"n_tasks":10,"usage_by_year":[{"year":"2020","papers":1},{"year":"2021","papers":1},{"year":"2024","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/dynamic-r-cnn"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=Dynamic%20R-CNN","read_at":"2026-10-05T00:55:24+00:00","query":"Dynamic R-CNN","kind":"paper","have":"unverified_code","tier":"harvested","verified_implementation":false,"level":1,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":{"arxiv_id":"2004.06002"},"resolution":"paper","resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":"same_paper","archive_paper_arxiv_id":"2004.06002","repositories":{"listed":3,"in_graph":3,"list_truncated":false,"strongest_link":"official"},"retrieve_with":"get_harvested_code_for_paper(arxiv_id='2004.06002')","name_competition":{"verdict":"sole_bearer","may_be_wrong_sense":false,"bearers_found":1,"served":{"arxiv_id":"2004.06002","citations":639},"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing else in this corpus is named 'Dynamic R-CNN'. That is a statement about this corpus and not about the field: short names are reused, and a sense we never collected cannot show up here. Confirm `served.arxiv_id` if you had a specific paper in mind."},"name_competition_text":null,"near_matches":null,"code_nearby":[],"code_nearby_caption":null,"origin_paper":{"arxiv_id":"2004.06002","page":"/paper/dynamic-r-cnn-towards-high-quality-object","syntology_url":"https://syntology.ai/paper/2004.06002","in_graph_layer":true,"samples":18,"ran":9,"n_ran_checked":9,"n_instrument":0,"unverified":9,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 1 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified","instrument_means":"failures of Syntology's instrument, not of the code"},"line":"harvested code stored, below machine verification (unverified_code; harvested), served level V1. Repositories: 3 listed of 3 in the graph, strongest link: official. The lookup matched a paper by its title, arXiv:2004.06002, not a method entry. This answer is about arXiv:2004.06002, the paper the archive credits with this method.","level_legend":{"state":"quoted","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","card_sha256":"479785a84658dd682a11b10237b3620d651d7f87799f5dc7add970aaa83f6d39","note":"Syntology's served verification levels, quoted verbatim from its MCP server card; a row is split where the card separates clauses with a double hyphen, and the separator is not reproduced","levels":[{"level":"V0","quoted":["imports"]},{"level":"V1","quoted":["executes against a synthesized fixture and returns a value of the recorded type"]},{"level":"V2","quoted":["two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs","neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)"]},{"level":"V3","quoted":["paper-derived property tests pass on both of those same two generations."]}],"no_rung":"No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results."}},"syntology_have_state":"loaded","record_sha256":"1ff5cbf024e044bd9978668c5e77a322d64b9fe171427da1ec2ecb207179b081","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}