{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:XKTCTJDUMONW4R5EVXSKZZCOTX","short_pith_number":"pith:XKTCTJDU","schema_version":"1.0","canonical_sha256":"baa629a474639b6e47a4ade4ace44e9df9c288ab1f88e6c1bed08fd0563011f2","source":{"kind":"arxiv","id":"2203.16317","version":2},"attestation_state":"computed","paper":{"title":"PseCo: Pseudo Labeling and Consistency Training for Semi-Supervised Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ding Liang, Gang Li, Shanshan Zhang, Xiang Li, Yichao Wu, Yujie Wang","submitted_at":"2022-03-30T13:59:22Z","abstract_excerpt":"In this paper, we delve into two key techniques in Semi-Supervised Object Detection (SSOD), namely pseudo labeling and consistency training. We observe that these two techniques currently neglect some important properties of object detection, hindering efficient learning on unlabeled data. Specifically, for pseudo labeling, existing works only focus on the classification score yet fail to guarantee the localization precision of pseudo boxes; For consistency training, the widely adopted random-resize training only considers the label-level consistency but misses the feature-level one, which als"},"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":"2203.16317","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-30T13:59:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3791e39e0676ca6057ac9f257cbe243fc37ceae30eaf5371d4efcbcf05dbe81b","abstract_canon_sha256":"387b317fc78f8d36e7d0b3271ad775206d5c3da9d78f22a1664e5d1dbcc2cd6b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:41:55.193439Z","signature_b64":"8Q0GCzEcS8ybH18GkXoh/imTex8TQ63Kx8RCwPAFLuCbhDgv0607h22a5h6cf1GaJiPJTd0XgiG5hCXvXTpDCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"baa629a474639b6e47a4ade4ace44e9df9c288ab1f88e6c1bed08fd0563011f2","last_reissued_at":"2026-07-05T04:41:55.192955Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:41:55.192955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PseCo: Pseudo Labeling and Consistency Training for Semi-Supervised Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ding Liang, Gang Li, Shanshan Zhang, Xiang Li, Yichao Wu, Yujie Wang","submitted_at":"2022-03-30T13:59:22Z","abstract_excerpt":"In this paper, we delve into two key techniques in Semi-Supervised Object Detection (SSOD), namely pseudo labeling and consistency training. We observe that these two techniques currently neglect some important properties of object detection, hindering efficient learning on unlabeled data. Specifically, for pseudo labeling, existing works only focus on the classification score yet fail to guarantee the localization precision of pseudo boxes; For consistency training, the widely adopted random-resize training only considers the label-level consistency but misses the feature-level one, which als"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.16317","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/2203.16317/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":"2203.16317","created_at":"2026-07-05T04:41:55.193011+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.16317v2","created_at":"2026-07-05T04:41:55.193011+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.16317","created_at":"2026-07-05T04:41:55.193011+00:00"},{"alias_kind":"pith_short_12","alias_value":"XKTCTJDUMONW","created_at":"2026-07-05T04:41:55.193011+00:00"},{"alias_kind":"pith_short_16","alias_value":"XKTCTJDUMONW4R5E","created_at":"2026-07-05T04:41:55.193011+00:00"},{"alias_kind":"pith_short_8","alias_value":"XKTCTJDU","created_at":"2026-07-05T04:41:55.193011+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.17536","citing_title":"Box for Mask and Mask for Box: weak losses for multi-task partially supervised learning","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XKTCTJDUMONW4R5EVXSKZZCOTX","json":"https://pith.science/pith/XKTCTJDUMONW4R5EVXSKZZCOTX.json","graph_json":"https://pith.science/api/pith-number/XKTCTJDUMONW4R5EVXSKZZCOTX/graph.json","events_json":"https://pith.science/api/pith-number/XKTCTJDUMONW4R5EVXSKZZCOTX/events.json","paper":"https://pith.science/paper/XKTCTJDU"},"agent_actions":{"view_html":"https://pith.science/pith/XKTCTJDUMONW4R5EVXSKZZCOTX","download_json":"https://pith.science/pith/XKTCTJDUMONW4R5EVXSKZZCOTX.json","view_paper":"https://pith.science/paper/XKTCTJDU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.16317&json=true","fetch_graph":"https://pith.science/api/pith-number/XKTCTJDUMONW4R5EVXSKZZCOTX/graph.json","fetch_events":"https://pith.science/api/pith-number/XKTCTJDUMONW4R5EVXSKZZCOTX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XKTCTJDUMONW4R5EVXSKZZCOTX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XKTCTJDUMONW4R5EVXSKZZCOTX/action/storage_attestation","attest_author":"https://pith.science/pith/XKTCTJDUMONW4R5EVXSKZZCOTX/action/author_attestation","sign_citation":"https://pith.science/pith/XKTCTJDUMONW4R5EVXSKZZCOTX/action/citation_signature","submit_replication":"https://pith.science/pith/XKTCTJDUMONW4R5EVXSKZZCOTX/action/replication_record"}},"created_at":"2026-07-05T04:41:55.193011+00:00","updated_at":"2026-07-05T04:41:55.193011+00:00"}