{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:6WJ7WQWEPHBKP3RAJZT7FATYGJ","short_pith_number":"pith:6WJ7WQWE","schema_version":"1.0","canonical_sha256":"f593fb42c479c2a7ee204e67f282783268fbc4c1f1d4f1dbdf90eb6f124664b3","source":{"kind":"arxiv","id":"2212.07784","version":2},"attestation_state":"computed","paper":{"title":"RTMDet: An Empirical Study of Designing Real-Time Object Detectors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengqi Lyu, Haian Huang, Kai Chen, Shilong Zhang, Wenwei Zhang, Yanyi Liu, Yudong Wang, Yue Zhou","submitted_at":"2022-12-14T18:50:20Z","abstract_excerpt":"In this paper, we aim to design an efficient real-time object detector that exceeds the YOLO series and is easily extensible for many object recognition tasks such as instance segmentation and rotated object detection. To obtain a more efficient model architecture, we explore an architecture that has compatible capacities in the backbone and neck, constructed by a basic building block that consists of large-kernel depth-wise convolutions. We further introduce soft labels when calculating matching costs in the dynamic label assignment to improve accuracy. Together with better training technique"},"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":"2212.07784","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-14T18:50:20Z","cross_cats_sorted":[],"title_canon_sha256":"5d9b680e7bf10fe7d4bcc81d9cc0443b05eb75027111fc6bd4f52ea88ad93f9c","abstract_canon_sha256":"848ef09ed36553d56b9fd6912f258fc0aafb84619456356d72a6819355fafe40"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:26:12.771217Z","signature_b64":"u8ylmdSVfE9x4l0IcTDC+P+knGHkmoNM/V5arejxxzSPG3Z0zAJ+OfVxGyxWieILkdx2ElzWKwLtY38nj/NJAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f593fb42c479c2a7ee204e67f282783268fbc4c1f1d4f1dbdf90eb6f124664b3","last_reissued_at":"2026-07-05T05:26:12.770706Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:26:12.770706Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RTMDet: An Empirical Study of Designing Real-Time Object Detectors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengqi Lyu, Haian Huang, Kai Chen, Shilong Zhang, Wenwei Zhang, Yanyi Liu, Yudong Wang, Yue Zhou","submitted_at":"2022-12-14T18:50:20Z","abstract_excerpt":"In this paper, we aim to design an efficient real-time object detector that exceeds the YOLO series and is easily extensible for many object recognition tasks such as instance segmentation and rotated object detection. To obtain a more efficient model architecture, we explore an architecture that has compatible capacities in the backbone and neck, constructed by a basic building block that consists of large-kernel depth-wise convolutions. We further introduce soft labels when calculating matching costs in the dynamic label assignment to improve accuracy. Together with better training technique"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.07784","kind":"arxiv","version":2},"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/2212.07784/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":"2212.07784","created_at":"2026-07-05T05:26:12.770771+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.07784v2","created_at":"2026-07-05T05:26:12.770771+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.07784","created_at":"2026-07-05T05:26:12.770771+00:00"},{"alias_kind":"pith_short_12","alias_value":"6WJ7WQWEPHBK","created_at":"2026-07-05T05:26:12.770771+00:00"},{"alias_kind":"pith_short_16","alias_value":"6WJ7WQWEPHBKP3RA","created_at":"2026-07-05T05:26:12.770771+00:00"},{"alias_kind":"pith_short_8","alias_value":"6WJ7WQWE","created_at":"2026-07-05T05:26:12.770771+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":20,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25312","citing_title":"LEVIRDet: A Million-Scale 159-Category Dataset and Foundation Model for Universal Remote Sensing Object Detection","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07368","citing_title":"Mitosis Detection in the Wild: Multi-Tumor and Context-Aware Generalization in the MIDOG 2025 Challenge","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03508","citing_title":"Structure-Guided Mixed Masked Pretraining and Spatial Continuity Regularization for Printed Circuit Board Defect Detection","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03568","citing_title":"Learned Non-Maximum Suppression for 3D Object Detection","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24508","citing_title":"FDDet: Achieving Data-Efficient Food Defect Detection Under Real-World Scenarios","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28261","citing_title":"MORI-Seg: Learning Morphological Geometry for Instance Segmentation without Instance Annotations","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23144","citing_title":"SLIP-RS: Structured-Attribute Language-Image Pre-Training for Remote Sensing Object Detection","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2305.07598","citing_title":"Hausdorff Distance Matching with Adaptive Query Denoising for Rotated Detection Transformer","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2501.15151","citing_title":"SpikeDet: Better Firing Patterns for Accurate and Energy-Efficient Object Detection with Spiking Neural Networks","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22200","citing_title":"OSS: Open Suturing Skills Vision-Based Assessment Challenge 2024-2025","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17772","citing_title":"Towards Universal Physical Adversarial Attacks via a Joint Multi-Objective and Multi-Model Optimization Framework","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2508.13401","citing_title":"AIM 2025 Rip Current Segmentation (RipSeg) Challenge Report","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08851","citing_title":"Geometrically Constrained Stenosis Editing in Coronary Angiography via Entropic Optimal Transport","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08851","citing_title":"Geometrically Constrained Stenosis Editing in Coronary Angiography via Entropic Optimal Transport","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23320","citing_title":"KAConvNet: Kolmogorov-Arnold Convolutional Networks for Vision Recognition","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04524","citing_title":"High-Fidelity Single-Image Head Modeling with Industry-Grade Topology","ref_index":191,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19834","citing_title":"KD-Judge: A Knowledge-Driven Automated Judge Framework for Functional Fitness Movements on Edge Devices","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18866","citing_title":"HMR-Net: Hierarchical Modular Routing for Cross-Domain Object Detection in Aerial Images","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13244","citing_title":"4th Workshop on Maritime Computer Vision (MaCVi): Challenge Overview","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02094","citing_title":"SignMAE: Segmentation-Driven Self-Supervised Learning for Sign Language Recognition","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6WJ7WQWEPHBKP3RAJZT7FATYGJ","json":"https://pith.science/pith/6WJ7WQWEPHBKP3RAJZT7FATYGJ.json","graph_json":"https://pith.science/api/pith-number/6WJ7WQWEPHBKP3RAJZT7FATYGJ/graph.json","events_json":"https://pith.science/api/pith-number/6WJ7WQWEPHBKP3RAJZT7FATYGJ/events.json","paper":"https://pith.science/paper/6WJ7WQWE"},"agent_actions":{"view_html":"https://pith.science/pith/6WJ7WQWEPHBKP3RAJZT7FATYGJ","download_json":"https://pith.science/pith/6WJ7WQWEPHBKP3RAJZT7FATYGJ.json","view_paper":"https://pith.science/paper/6WJ7WQWE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.07784&json=true","fetch_graph":"https://pith.science/api/pith-number/6WJ7WQWEPHBKP3RAJZT7FATYGJ/graph.json","fetch_events":"https://pith.science/api/pith-number/6WJ7WQWEPHBKP3RAJZT7FATYGJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6WJ7WQWEPHBKP3RAJZT7FATYGJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6WJ7WQWEPHBKP3RAJZT7FATYGJ/action/storage_attestation","attest_author":"https://pith.science/pith/6WJ7WQWEPHBKP3RAJZT7FATYGJ/action/author_attestation","sign_citation":"https://pith.science/pith/6WJ7WQWEPHBKP3RAJZT7FATYGJ/action/citation_signature","submit_replication":"https://pith.science/pith/6WJ7WQWEPHBKP3RAJZT7FATYGJ/action/replication_record"}},"created_at":"2026-07-05T05:26:12.770771+00:00","updated_at":"2026-07-05T05:26:12.770771+00:00"}