{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:3E5F5BFICVH73NX4J74IVWAMLH","short_pith_number":"pith:3E5F5BFI","schema_version":"1.0","canonical_sha256":"d93a5e84a8154ffdb6fc4ff88ad80c59d0193c1b7171da46b5a44ec7b18822a3","source":{"kind":"arxiv","id":"2011.12450","version":2},"attestation_state":"computed","paper":{"title":"Sparse R-CNN: End-to-End Object Detection with Learnable Proposals","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changhu Wang, Chenfeng Xu, Lei Li, Masayoshi Tomizuka, Peize Sun, Ping Luo, Rufeng Zhang, Tao Kong, Wei Zhan, Yi Jiang, Zehuan Yuan","submitted_at":"2020-11-25T00:01:28Z","abstract_excerpt":"We present Sparse R-CNN, a purely sparse method for object detection in images. Existing works on object detection heavily rely on dense object candidates, such as $k$ anchor boxes pre-defined on all grids of image feature map of size $H\\times W$. In our method, however, a fixed sparse set of learned object proposals, total length of $N$, are provided to object recognition head to perform classification and location. By eliminating $HWk$ (up to hundreds of thousands) hand-designed object candidates to $N$ (e.g. 100) learnable proposals, Sparse R-CNN completely avoids all efforts related to obj"},"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":"2011.12450","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-11-25T00:01:28Z","cross_cats_sorted":[],"title_canon_sha256":"c2ec569e4cadd252d157bfe76920c641312a72086cb045b54d227da9008c2251","abstract_canon_sha256":"762e36d3bfac1b2cb6c4151e5201c5a0426076f6a851b29e1270da604998fd98"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:34:43.964688Z","signature_b64":"rKVnLXW4o2bC7fQrIKS03OQ9fWH1ln20sS7yIGpKJY94tPD4MS4iQxUSsUSOr+c0WajaY6KFH/vRAKwWDK5FDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d93a5e84a8154ffdb6fc4ff88ad80c59d0193c1b7171da46b5a44ec7b18822a3","last_reissued_at":"2026-07-05T02:34:43.964199Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:34:43.964199Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sparse R-CNN: End-to-End Object Detection with Learnable Proposals","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changhu Wang, Chenfeng Xu, Lei Li, Masayoshi Tomizuka, Peize Sun, Ping Luo, Rufeng Zhang, Tao Kong, Wei Zhan, Yi Jiang, Zehuan Yuan","submitted_at":"2020-11-25T00:01:28Z","abstract_excerpt":"We present Sparse R-CNN, a purely sparse method for object detection in images. Existing works on object detection heavily rely on dense object candidates, such as $k$ anchor boxes pre-defined on all grids of image feature map of size $H\\times W$. In our method, however, a fixed sparse set of learned object proposals, total length of $N$, are provided to object recognition head to perform classification and location. By eliminating $HWk$ (up to hundreds of thousands) hand-designed object candidates to $N$ (e.g. 100) learnable proposals, Sparse R-CNN completely avoids all efforts related to obj"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.12450","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/2011.12450/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":"2011.12450","created_at":"2026-07-05T02:34:43.964250+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.12450v2","created_at":"2026-07-05T02:34:43.964250+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.12450","created_at":"2026-07-05T02:34:43.964250+00:00"},{"alias_kind":"pith_short_12","alias_value":"3E5F5BFICVH7","created_at":"2026-07-05T02:34:43.964250+00:00"},{"alias_kind":"pith_short_16","alias_value":"3E5F5BFICVH73NX4","created_at":"2026-07-05T02:34:43.964250+00:00"},{"alias_kind":"pith_short_8","alias_value":"3E5F5BFI","created_at":"2026-07-05T02:34:43.964250+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2103.14030","citing_title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","ref_index":56,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3E5F5BFICVH73NX4J74IVWAMLH","json":"https://pith.science/pith/3E5F5BFICVH73NX4J74IVWAMLH.json","graph_json":"https://pith.science/api/pith-number/3E5F5BFICVH73NX4J74IVWAMLH/graph.json","events_json":"https://pith.science/api/pith-number/3E5F5BFICVH73NX4J74IVWAMLH/events.json","paper":"https://pith.science/paper/3E5F5BFI"},"agent_actions":{"view_html":"https://pith.science/pith/3E5F5BFICVH73NX4J74IVWAMLH","download_json":"https://pith.science/pith/3E5F5BFICVH73NX4J74IVWAMLH.json","view_paper":"https://pith.science/paper/3E5F5BFI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.12450&json=true","fetch_graph":"https://pith.science/api/pith-number/3E5F5BFICVH73NX4J74IVWAMLH/graph.json","fetch_events":"https://pith.science/api/pith-number/3E5F5BFICVH73NX4J74IVWAMLH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3E5F5BFICVH73NX4J74IVWAMLH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3E5F5BFICVH73NX4J74IVWAMLH/action/storage_attestation","attest_author":"https://pith.science/pith/3E5F5BFICVH73NX4J74IVWAMLH/action/author_attestation","sign_citation":"https://pith.science/pith/3E5F5BFICVH73NX4J74IVWAMLH/action/citation_signature","submit_replication":"https://pith.science/pith/3E5F5BFICVH73NX4J74IVWAMLH/action/replication_record"}},"created_at":"2026-07-05T02:34:43.964250+00:00","updated_at":"2026-07-05T02:34:43.964250+00:00"}