{"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/varifocal-loss","slug":"varifocal-loss","name":"Varifocal Loss","full_name":"Varifocal Loss","full_name_withheld":false,"description_markdown":"**Varifocal Loss** is a loss function for training a dense object detector to predict the IACS, inspired by [focal loss](https://paperswithcode.com/method/focal-loss). Unlike the focal loss that deals with positives and negatives equally, Varifocal Loss treats them asymmetrically.\r\n\r\n$$ VFL\\left(p, q\\right) = −q\\left(q\\log\\left(p\\right) + \\left(1 − q\\right)\\log\\left(1 − p\\right)\\right) \\text{ if } q > 0 $$\r\n\r\n$$ VFL\\left(p, q\\right) = −\\alpha{p^{\\gamma}}\\log\\left(1-p\\right) $$\r\n\r\nwhere $p$ is the predicted IACS and $q$ is the target IoU score.\r\n\r\nFor a positive training example, $q$ is set as the IoU between the generated bounding box and the ground-truth one\r\n(gt IoU), whereas for a negative training example, the training target $q$ for all classes is $0$.","description_state":"present","introduced_year":null,"introduced_by":{"title":"VarifocalNet: An IoU-aware Dense Object Detector","paper":"/paper/varifocalnet-an-iou-aware-dense-object","first_author":"Haoyang Zhang","n_authors":4,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/varifocalnet-an-iou-aware-dense-object"},"source":{"url":"https://arxiv.org/abs/2008.13367v2","title":"VarifocalNet: An IoU-aware Dense Object Detector","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"General","area_id":"general","collection":"Loss Functions","url":"/methods/category/loss-functions","pwc_aliases":[]}],"n_papers_tagged":8,"archive_num_papers":8,"papers_newest_first":[{"paper":null,"slug":"class-imbalance-correction-for-improved","title":"Class Imbalance Correction for Improved Universal Lesion Detection and Tagging in CT","date":"2025-04-08","arxiv_id":"2504.05591","n_code_links":0,"syntology":null},{"paper":null,"slug":"universal-lymph-node-detection-in","title":"Universal Lymph Node Detection in Multiparametric MRI with Selective Augmentation","date":"2025-04-07","arxiv_id":"2504.05196","n_code_links":0,"syntology":null},{"paper":null,"slug":"comparing-surface-landmine-object-detection","title":"Comparing Surface Landmine Object Detection Models on a New Drone Flyby Dataset","date":"2024-10-17","arxiv_id":"2410.19807","n_code_links":0,"syntology":null},{"paper":"/paper/how-to-train-an-accurate-and-efficient-object","slug":"how-to-train-an-accurate-and-efficient-object","title":"How to Train an Accurate and Efficient Object Detection Model on Any Dataset","date":"2022-11-30","arxiv_id":"2211.17170","n_code_links":1,"syntology":null},{"paper":null,"slug":"universal-lymph-node-detection-in-t2-mri","title":"Universal Lymph Node Detection in T2 MRI using Neural Networks","date":"2022-03-31","arxiv_id":"2204.00622","n_code_links":0,"syntology":null},{"paper":"/paper/slicing-aided-hyper-inference-and-fine-tuning","slug":"slicing-aided-hyper-inference-and-fine-tuning","title":"Slicing Aided Hyper Inference and Fine-tuning for Small Object Detection","date":"2022-02-14","arxiv_id":"2202.06934","n_code_links":6,"syntology":{"ran":18,"of":19,"n_ran_checked":17,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"18 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["fcakyon/sahi-benchmark","obss/sahi"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/swa-object-detection","slug":"swa-object-detection","title":"SWA Object Detection","date":"2020-12-23","arxiv_id":"2012.12645","n_code_links":2,"syntology":null},{"paper":"/paper/varifocalnet-an-iou-aware-dense-object","slug":"varifocalnet-an-iou-aware-dense-object","title":"VarifocalNet: An IoU-aware Dense Object Detector","date":"2020-08-31","arxiv_id":"2008.13367","n_code_links":4,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["hyz-xmaster/VarifocalNet"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}}],"papers_shown":8,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":8,"with_a_code_link":4,"where_syntology_ran_a_sample":2,"not_listed_spam_title":0,"listed":8,"listed_where_code_ran":2,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":2,"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":2,"papers_where_code_ran_first_page":"/method/varifocal-loss/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/varifocal-loss/papers/ran/1","json":"/method/varifocal-loss/papers/ran/1.json","rows":2}],"tasks":[{"task":"/task/object-detection","name":"Object Detection","papers":5},{"task":"/task/object-detection-1","name":"object-detection","papers":4},{"task":"/task/object","name":"Object","papers":3},{"task":"/task/sensitivity","name":"Sensitivity","papers":2},{"task":null,"name":"CPU","papers":1},{"task":"/task/classification","name":"General Classification","papers":1},{"task":"/task/instance-segmentation","name":"Instance Segmentation","papers":1},{"task":"/task/landmine","name":"Landmine","papers":1},{"task":"/task/lesion-detection","name":"Lesion Detection","papers":1},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":1},{"task":"/task/small-object-detection","name":"Small Object Detection","papers":1},{"task":"/task/tag","name":"TAG","papers":1}],"tasks_shown":12,"n_tasks":12,"usage_by_year":[{"year":"2020","papers":2},{"year":"2022","papers":3},{"year":"2024","papers":1},{"year":"2025","papers":2}],"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/varifocal-loss"},"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=Varifocal%20Loss","read_at":"2026-10-05T01:03:35+00:00","query":"Varifocal Loss","kind":"method","have":"declared_code","tier":"repo_known","verified_implementation":false,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":{"method":"Varifocal","origin_arxiv_id":"2210.12400"},"resolution":"token_match","resolved_name_differs":true,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":"different_paper","archive_paper_arxiv_id":"2008.13367","repositories":{"listed":1,"in_graph":1,"list_truncated":false,"strongest_link":"official"},"retrieve_with":null,"name_competition":{"verdict":"sole_bearer","may_be_wrong_sense":false,"bearers_found":1,"served":{"arxiv_id":"2210.12400","citations":41},"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing else in this corpus is named 'Varifocal Loss'. 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":"2210.12400","page":"/paper/varifocal-question-generation-for-fact","syntology_url":"https://syntology.ai/paper/2210.12400","in_graph_layer":false,"samples":0},"line":"for a different name, 'Varifocal', about another paper, arXiv:2210.12400: repository known, no verified implementation (declared_code; repositories: 1 listed of 1 in the graph, strongest link: official). The lookup matched a different name in Syntology's graph, 'Varifocal' (resolution: token_match); this answer is about that name. About another paper: this answer is about arXiv:2210.12400, while the archive credits arXiv:2008.13367.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"fa90ac4c7f8a186a0c73e888a2434cc261cde9987fc03368a11acadb74357308","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}