{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:NX2JGVNZCCE3G2DERNRR3SSFTO","short_pith_number":"pith:NX2JGVNZ","schema_version":"1.0","canonical_sha256":"6df49355b91089b368648b631dca459b9a45cd7444f7e83e0abba88e172d896b","source":{"kind":"arxiv","id":"2007.03496","version":3},"attestation_state":"computed","paper":{"title":"AutoAssign: Differentiable Label Assignment for Dense Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Benjin Zhu, Fuhang Zong, Jianfeng Wang, Jian Sun, Songtao Liu, Zeming Li, Zhengkai Jiang","submitted_at":"2020-07-07T14:32:21Z","abstract_excerpt":"Determining positive/negative samples for object detection is known as label assignment. Here we present an anchor-free detector named AutoAssign. It requires little human knowledge and achieves appearance-aware through a fully differentiable weighting mechanism. During training, to both satisfy the prior distribution of data and adapt to category characteristics, we present Center Weighting to adjust the category-specific prior distributions. To adapt to object appearances, Confidence Weighting is proposed to adjust the specific assign strategy of each instance. The two weighting modules are "},"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":"2007.03496","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-07-07T14:32:21Z","cross_cats_sorted":[],"title_canon_sha256":"239dfc7ea052b10184062e350030d4a9e3a077963c5c322cbe63f6ccd9e553a8","abstract_canon_sha256":"138dd1ad8ba064e51ce135dcda369e41c9b67533076ab9a4920abb6990c85a2f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:54:29.374855Z","signature_b64":"Ru02gT6udpa8A7UF+8iufF1YK+3qLsSDARdFgwbfrpADoKaCanK/1g207MijJr/cj1Kw3QkljbsYEAz2Ck/1Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6df49355b91089b368648b631dca459b9a45cd7444f7e83e0abba88e172d896b","last_reissued_at":"2026-07-05T01:54:29.374400Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:54:29.374400Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AutoAssign: Differentiable Label Assignment for Dense Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Benjin Zhu, Fuhang Zong, Jianfeng Wang, Jian Sun, Songtao Liu, Zeming Li, Zhengkai Jiang","submitted_at":"2020-07-07T14:32:21Z","abstract_excerpt":"Determining positive/negative samples for object detection is known as label assignment. Here we present an anchor-free detector named AutoAssign. It requires little human knowledge and achieves appearance-aware through a fully differentiable weighting mechanism. During training, to both satisfy the prior distribution of data and adapt to category characteristics, we present Center Weighting to adjust the category-specific prior distributions. To adapt to object appearances, Confidence Weighting is proposed to adjust the specific assign strategy of each instance. The two weighting modules are "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.03496","kind":"arxiv","version":3},"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/2007.03496/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":"2007.03496","created_at":"2026-07-05T01:54:29.374464+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.03496v3","created_at":"2026-07-05T01:54:29.374464+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.03496","created_at":"2026-07-05T01:54:29.374464+00:00"},{"alias_kind":"pith_short_12","alias_value":"NX2JGVNZCCE3","created_at":"2026-07-05T01:54:29.374464+00:00"},{"alias_kind":"pith_short_16","alias_value":"NX2JGVNZCCE3G2DE","created_at":"2026-07-05T01:54:29.374464+00:00"},{"alias_kind":"pith_short_8","alias_value":"NX2JGVNZ","created_at":"2026-07-05T01:54:29.374464+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.12524","citing_title":"YOLOv12: Attention-Centric Real-Time Object Detectors","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2107.08430","citing_title":"YOLOX: Exceeding YOLO Series in 2021","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NX2JGVNZCCE3G2DERNRR3SSFTO","json":"https://pith.science/pith/NX2JGVNZCCE3G2DERNRR3SSFTO.json","graph_json":"https://pith.science/api/pith-number/NX2JGVNZCCE3G2DERNRR3SSFTO/graph.json","events_json":"https://pith.science/api/pith-number/NX2JGVNZCCE3G2DERNRR3SSFTO/events.json","paper":"https://pith.science/paper/NX2JGVNZ"},"agent_actions":{"view_html":"https://pith.science/pith/NX2JGVNZCCE3G2DERNRR3SSFTO","download_json":"https://pith.science/pith/NX2JGVNZCCE3G2DERNRR3SSFTO.json","view_paper":"https://pith.science/paper/NX2JGVNZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.03496&json=true","fetch_graph":"https://pith.science/api/pith-number/NX2JGVNZCCE3G2DERNRR3SSFTO/graph.json","fetch_events":"https://pith.science/api/pith-number/NX2JGVNZCCE3G2DERNRR3SSFTO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NX2JGVNZCCE3G2DERNRR3SSFTO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NX2JGVNZCCE3G2DERNRR3SSFTO/action/storage_attestation","attest_author":"https://pith.science/pith/NX2JGVNZCCE3G2DERNRR3SSFTO/action/author_attestation","sign_citation":"https://pith.science/pith/NX2JGVNZCCE3G2DERNRR3SSFTO/action/citation_signature","submit_replication":"https://pith.science/pith/NX2JGVNZCCE3G2DERNRR3SSFTO/action/replication_record"}},"created_at":"2026-07-05T01:54:29.374464+00:00","updated_at":"2026-07-05T01:54:29.374464+00:00"}