{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:AIMM5CQKAEROBKOSKQLROXKNIE","short_pith_number":"pith:AIMM5CQK","schema_version":"1.0","canonical_sha256":"0218ce8a0a0122e0a9d25417175d4d412ec505c35db5f9385bb288df1beffc37","source":{"kind":"arxiv","id":"2103.14242","version":1},"attestation_state":"computed","paper":{"title":"Learning from Pixel-Level Label Noise: A New Perspective for Semi-Supervised Semantic Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Mengyang Pu, Qingji Guan, Rumeng Yi, Runsheng Zhang, Yaping Huang","submitted_at":"2021-03-26T03:23:21Z","abstract_excerpt":"This paper addresses semi-supervised semantic segmentation by exploiting a small set of images with pixel-level annotations (strong supervisions) and a large set of images with only image-level annotations (weak supervisions). Most existing approaches aim to generate accurate pixel-level labels from weak supervisions. However, we observe that those generated labels still inevitably contain noisy labels. Motivated by this observation, we present a novel perspective and formulate this task as a problem of learning with pixel-level label noise. Existing noisy label methods, nevertheless, mainly a"},"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":"2103.14242","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-03-26T03:23:21Z","cross_cats_sorted":[],"title_canon_sha256":"a537194ec9ad7947f84c5d437d5c513a6138a43229b69bd2e58faf5cdc9c5b91","abstract_canon_sha256":"1fda9de08b37df4b5c74d27194ad32e532eb8e46d2a00ea7b13a0fdb2c2ffcfe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:47:16.688550Z","signature_b64":"7IbpCUkPgtC/Ijo+o7+eMS+4ky0R4fhHIMnD8dSi0F3KihU0eSIJFlCK5dOZs0sk01eVT6JXa8LO3CKA6GwhBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0218ce8a0a0122e0a9d25417175d4d412ec505c35db5f9385bb288df1beffc37","last_reissued_at":"2026-07-05T03:47:16.687989Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:47:16.687989Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning from Pixel-Level Label Noise: A New Perspective for Semi-Supervised Semantic Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Mengyang Pu, Qingji Guan, Rumeng Yi, Runsheng Zhang, Yaping Huang","submitted_at":"2021-03-26T03:23:21Z","abstract_excerpt":"This paper addresses semi-supervised semantic segmentation by exploiting a small set of images with pixel-level annotations (strong supervisions) and a large set of images with only image-level annotations (weak supervisions). Most existing approaches aim to generate accurate pixel-level labels from weak supervisions. However, we observe that those generated labels still inevitably contain noisy labels. Motivated by this observation, we present a novel perspective and formulate this task as a problem of learning with pixel-level label noise. Existing noisy label methods, nevertheless, mainly a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.14242","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/2103.14242/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":"2103.14242","created_at":"2026-07-05T03:47:16.688049+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.14242v1","created_at":"2026-07-05T03:47:16.688049+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.14242","created_at":"2026-07-05T03:47:16.688049+00:00"},{"alias_kind":"pith_short_12","alias_value":"AIMM5CQKAERO","created_at":"2026-07-05T03:47:16.688049+00:00"},{"alias_kind":"pith_short_16","alias_value":"AIMM5CQKAEROBKOS","created_at":"2026-07-05T03:47:16.688049+00:00"},{"alias_kind":"pith_short_8","alias_value":"AIMM5CQK","created_at":"2026-07-05T03:47:16.688049+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/AIMM5CQKAEROBKOSKQLROXKNIE","json":"https://pith.science/pith/AIMM5CQKAEROBKOSKQLROXKNIE.json","graph_json":"https://pith.science/api/pith-number/AIMM5CQKAEROBKOSKQLROXKNIE/graph.json","events_json":"https://pith.science/api/pith-number/AIMM5CQKAEROBKOSKQLROXKNIE/events.json","paper":"https://pith.science/paper/AIMM5CQK"},"agent_actions":{"view_html":"https://pith.science/pith/AIMM5CQKAEROBKOSKQLROXKNIE","download_json":"https://pith.science/pith/AIMM5CQKAEROBKOSKQLROXKNIE.json","view_paper":"https://pith.science/paper/AIMM5CQK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.14242&json=true","fetch_graph":"https://pith.science/api/pith-number/AIMM5CQKAEROBKOSKQLROXKNIE/graph.json","fetch_events":"https://pith.science/api/pith-number/AIMM5CQKAEROBKOSKQLROXKNIE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AIMM5CQKAEROBKOSKQLROXKNIE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AIMM5CQKAEROBKOSKQLROXKNIE/action/storage_attestation","attest_author":"https://pith.science/pith/AIMM5CQKAEROBKOSKQLROXKNIE/action/author_attestation","sign_citation":"https://pith.science/pith/AIMM5CQKAEROBKOSKQLROXKNIE/action/citation_signature","submit_replication":"https://pith.science/pith/AIMM5CQKAEROBKOSKQLROXKNIE/action/replication_record"}},"created_at":"2026-07-05T03:47:16.688049+00:00","updated_at":"2026-07-05T03:47:16.688049+00:00"}