{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EE56DP7TV7XO7INZBWLFSJUEJQ","short_pith_number":"pith:EE56DP7T","schema_version":"1.0","canonical_sha256":"213be1bff3afeeefa1b90d965926844c1941394a951d4f8016ed7e7223acbff0","source":{"kind":"arxiv","id":"2308.05359","version":1},"attestation_state":"computed","paper":{"title":"Pseudo-label Alignment for Semi-supervised Instance Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Annan Shu, Chen Chen, Guannan Jiang, Jie Hu, Liujuan Cao, Rongrong Ji, Shengchuan Zhang","submitted_at":"2023-08-10T05:56:53Z","abstract_excerpt":"Pseudo-labeling is significant for semi-supervised instance segmentation, which generates instance masks and classes from unannotated images for subsequent training. However, in existing pipelines, pseudo-labels that contain valuable information may be directly filtered out due to mismatches in class and mask quality. To address this issue, we propose a novel framework, called pseudo-label aligning instance segmentation (PAIS), in this paper. In PAIS, we devise a dynamic aligning loss (DALoss) that adjusts the weights of semi-supervised loss terms with varying class and mask score pairs. Throu"},"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":"2308.05359","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-10T05:56:53Z","cross_cats_sorted":[],"title_canon_sha256":"b3a0eabb533907c70ce0a7dfafb78780d1e29d62aa7fe7b3297f18d8bd3c959a","abstract_canon_sha256":"434da4e9d29a7fea6258d47407437639aafcb3e6347568f1445c0a0889cba104"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:39:59.491303Z","signature_b64":"L1FSthvevt0r3xSO15PZ9XHh+c3UD0b46TFTdKzGmJUG1T5Cbf5H53gXzOnqR+RVX7EMXyrZEeJo1QRixQ4GAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"213be1bff3afeeefa1b90d965926844c1941394a951d4f8016ed7e7223acbff0","last_reissued_at":"2026-07-05T06:39:59.490910Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:39:59.490910Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pseudo-label Alignment for Semi-supervised Instance Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Annan Shu, Chen Chen, Guannan Jiang, Jie Hu, Liujuan Cao, Rongrong Ji, Shengchuan Zhang","submitted_at":"2023-08-10T05:56:53Z","abstract_excerpt":"Pseudo-labeling is significant for semi-supervised instance segmentation, which generates instance masks and classes from unannotated images for subsequent training. However, in existing pipelines, pseudo-labels that contain valuable information may be directly filtered out due to mismatches in class and mask quality. To address this issue, we propose a novel framework, called pseudo-label aligning instance segmentation (PAIS), in this paper. In PAIS, we devise a dynamic aligning loss (DALoss) that adjusts the weights of semi-supervised loss terms with varying class and mask score pairs. Throu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.05359","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/2308.05359/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":"2308.05359","created_at":"2026-07-05T06:39:59.490968+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.05359v1","created_at":"2026-07-05T06:39:59.490968+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.05359","created_at":"2026-07-05T06:39:59.490968+00:00"},{"alias_kind":"pith_short_12","alias_value":"EE56DP7TV7XO","created_at":"2026-07-05T06:39:59.490968+00:00"},{"alias_kind":"pith_short_16","alias_value":"EE56DP7TV7XO7INZ","created_at":"2026-07-05T06:39:59.490968+00:00"},{"alias_kind":"pith_short_8","alias_value":"EE56DP7T","created_at":"2026-07-05T06:39:59.490968+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EE56DP7TV7XO7INZBWLFSJUEJQ","json":"https://pith.science/pith/EE56DP7TV7XO7INZBWLFSJUEJQ.json","graph_json":"https://pith.science/api/pith-number/EE56DP7TV7XO7INZBWLFSJUEJQ/graph.json","events_json":"https://pith.science/api/pith-number/EE56DP7TV7XO7INZBWLFSJUEJQ/events.json","paper":"https://pith.science/paper/EE56DP7T"},"agent_actions":{"view_html":"https://pith.science/pith/EE56DP7TV7XO7INZBWLFSJUEJQ","download_json":"https://pith.science/pith/EE56DP7TV7XO7INZBWLFSJUEJQ.json","view_paper":"https://pith.science/paper/EE56DP7T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.05359&json=true","fetch_graph":"https://pith.science/api/pith-number/EE56DP7TV7XO7INZBWLFSJUEJQ/graph.json","fetch_events":"https://pith.science/api/pith-number/EE56DP7TV7XO7INZBWLFSJUEJQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EE56DP7TV7XO7INZBWLFSJUEJQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EE56DP7TV7XO7INZBWLFSJUEJQ/action/storage_attestation","attest_author":"https://pith.science/pith/EE56DP7TV7XO7INZBWLFSJUEJQ/action/author_attestation","sign_citation":"https://pith.science/pith/EE56DP7TV7XO7INZBWLFSJUEJQ/action/citation_signature","submit_replication":"https://pith.science/pith/EE56DP7TV7XO7INZBWLFSJUEJQ/action/replication_record"}},"created_at":"2026-07-05T06:39:59.490968+00:00","updated_at":"2026-07-05T06:39:59.490968+00:00"}