{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:TQN56TAPCLMCYUCSGOQ2O7I2TZ","short_pith_number":"pith:TQN56TAP","schema_version":"1.0","canonical_sha256":"9c1bdf4c0f12d82c505233a1a77d1a9e659e154dddedd86f15343e0701895d0b","source":{"kind":"arxiv","id":"1911.08287","version":1},"attestation_state":"computed","paper":{"title":"Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongwei Ren, Jinze Li, Ping Wang, Rongguang Ye, Wei Liu, Zhaohui Zheng","submitted_at":"2019-11-19T14:20:07Z","abstract_excerpt":"Bounding box regression is the crucial step in object detection. In existing methods, while $\\ell_n$-norm loss is widely adopted for bounding box regression, it is not tailored to the evaluation metric, i.e., Intersection over Union (IoU). Recently, IoU loss and generalized IoU (GIoU) loss have been proposed to benefit the IoU metric, but still suffer from the problems of slow convergence and inaccurate regression. In this paper, we propose a Distance-IoU (DIoU) loss by incorporating the normalized distance between the predicted box and the target box, which converges much faster in training t"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1911.08287","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-11-19T14:20:07Z","cross_cats_sorted":[],"title_canon_sha256":"b2ea812c6958a39d2106a358ef2fecce0dbd1347c1e211b51a9ad8e6e5682bdf","abstract_canon_sha256":"5d6d666f26eaa776db756737a812146f777c5f82ce63f4abd25af12d66fd7e67"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:20:27.090557Z","signature_b64":"Tm1t0ox/lyJZ8GhjKyi2rO2i5S6j/WqEQWlryqCqLp2S6Vxma8TGJRgUGgQdCg2aHfk1/OnraSC9jZO3BPFxAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c1bdf4c0f12d82c505233a1a77d1a9e659e154dddedd86f15343e0701895d0b","last_reissued_at":"2026-07-05T00:20:27.090070Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:20:27.090070Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongwei Ren, Jinze Li, Ping Wang, Rongguang Ye, Wei Liu, Zhaohui Zheng","submitted_at":"2019-11-19T14:20:07Z","abstract_excerpt":"Bounding box regression is the crucial step in object detection. In existing methods, while $\\ell_n$-norm loss is widely adopted for bounding box regression, it is not tailored to the evaluation metric, i.e., Intersection over Union (IoU). Recently, IoU loss and generalized IoU (GIoU) loss have been proposed to benefit the IoU metric, but still suffer from the problems of slow convergence and inaccurate regression. In this paper, we propose a Distance-IoU (DIoU) loss by incorporating the normalized distance between the predicted box and the target box, which converges much faster in training t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.08287","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1911.08287/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1911.08287","created_at":"2026-07-05T00:20:27.090128+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.08287v1","created_at":"2026-07-05T00:20:27.090128+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.08287","created_at":"2026-07-05T00:20:27.090128+00:00"},{"alias_kind":"pith_short_12","alias_value":"TQN56TAPCLMC","created_at":"2026-07-05T00:20:27.090128+00:00"},{"alias_kind":"pith_short_16","alias_value":"TQN56TAPCLMCYUCS","created_at":"2026-07-05T00:20:27.090128+00:00"},{"alias_kind":"pith_short_8","alias_value":"TQN56TAP","created_at":"2026-07-05T00:20:27.090128+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.13278","citing_title":"DroneScan-YOLO: Redundancy-Aware Lightweight Detection for Tiny Objects in UAV Imagery","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TQN56TAPCLMCYUCSGOQ2O7I2TZ","json":"https://pith.science/pith/TQN56TAPCLMCYUCSGOQ2O7I2TZ.json","graph_json":"https://pith.science/api/pith-number/TQN56TAPCLMCYUCSGOQ2O7I2TZ/graph.json","events_json":"https://pith.science/api/pith-number/TQN56TAPCLMCYUCSGOQ2O7I2TZ/events.json","paper":"https://pith.science/paper/TQN56TAP"},"agent_actions":{"view_html":"https://pith.science/pith/TQN56TAPCLMCYUCSGOQ2O7I2TZ","download_json":"https://pith.science/pith/TQN56TAPCLMCYUCSGOQ2O7I2TZ.json","view_paper":"https://pith.science/paper/TQN56TAP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.08287&json=true","fetch_graph":"https://pith.science/api/pith-number/TQN56TAPCLMCYUCSGOQ2O7I2TZ/graph.json","fetch_events":"https://pith.science/api/pith-number/TQN56TAPCLMCYUCSGOQ2O7I2TZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TQN56TAPCLMCYUCSGOQ2O7I2TZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TQN56TAPCLMCYUCSGOQ2O7I2TZ/action/storage_attestation","attest_author":"https://pith.science/pith/TQN56TAPCLMCYUCSGOQ2O7I2TZ/action/author_attestation","sign_citation":"https://pith.science/pith/TQN56TAPCLMCYUCSGOQ2O7I2TZ/action/citation_signature","submit_replication":"https://pith.science/pith/TQN56TAPCLMCYUCSGOQ2O7I2TZ/action/replication_record"}},"created_at":"2026-07-05T00:20:27.090128+00:00","updated_at":"2026-07-05T00:20:27.090128+00:00"}