{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:C7MZAHK6AEBXL3TQG3GWHLCF6K","short_pith_number":"pith:C7MZAHK6","schema_version":"1.0","canonical_sha256":"17d9901d5e010375ee7036cd63ac45f2897e2488b73aee97b5345e251185489d","source":{"kind":"arxiv","id":"2403.13225","version":1},"attestation_state":"computed","paper":{"title":"Modeling the Label Distributions for Weakly-Supervised Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.IV","authors_text":"Hao Chen, Jiayi Ma, Leyuan Fang, Linshan Wu, Shutao Li, Yunchao Wei, Zhun Zhong","submitted_at":"2024-03-20T01:07:46Z","abstract_excerpt":"Weakly-Supervised Semantic Segmentation (WSSS) aims to train segmentation models by weak labels, which is receiving significant attention due to its low annotation cost. Existing approaches focus on generating pseudo labels for supervision while largely ignoring to leverage the inherent semantic correlation among different pseudo labels. We observe that pseudo-labeled pixels that are close to each other in the feature space are more likely to share the same class, and those closer to the distribution centers tend to have higher confidence. Motivated by this, we propose to model the underlying "},"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":"2403.13225","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2024-03-20T01:07:46Z","cross_cats_sorted":[],"title_canon_sha256":"ece0092778000c46422d12475e89c8edc72b711dc3ecea053b68421e04820cb3","abstract_canon_sha256":"8647f9d8c0a45575266db734cd7112fd1e21dac169cecd80a3f43bb1a936db9e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:58:33.041619Z","signature_b64":"VOsPM3bWqwpVHQMBGhNGcpjoj77YEcn/cun6QXDk0mhA2+L0A7SVTf9JRcbBgJAO8SB8WHFv0w72CUBa0+SaCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17d9901d5e010375ee7036cd63ac45f2897e2488b73aee97b5345e251185489d","last_reissued_at":"2026-07-05T07:58:33.041069Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:58:33.041069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Modeling the Label Distributions for Weakly-Supervised Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.IV","authors_text":"Hao Chen, Jiayi Ma, Leyuan Fang, Linshan Wu, Shutao Li, Yunchao Wei, Zhun Zhong","submitted_at":"2024-03-20T01:07:46Z","abstract_excerpt":"Weakly-Supervised Semantic Segmentation (WSSS) aims to train segmentation models by weak labels, which is receiving significant attention due to its low annotation cost. Existing approaches focus on generating pseudo labels for supervision while largely ignoring to leverage the inherent semantic correlation among different pseudo labels. We observe that pseudo-labeled pixels that are close to each other in the feature space are more likely to share the same class, and those closer to the distribution centers tend to have higher confidence. Motivated by this, we propose to model the underlying "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.13225","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/2403.13225/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":"2403.13225","created_at":"2026-07-05T07:58:33.041133+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.13225v1","created_at":"2026-07-05T07:58:33.041133+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.13225","created_at":"2026-07-05T07:58:33.041133+00:00"},{"alias_kind":"pith_short_12","alias_value":"C7MZAHK6AEBX","created_at":"2026-07-05T07:58:33.041133+00:00"},{"alias_kind":"pith_short_16","alias_value":"C7MZAHK6AEBXL3TQ","created_at":"2026-07-05T07:58:33.041133+00:00"},{"alias_kind":"pith_short_8","alias_value":"C7MZAHK6","created_at":"2026-07-05T07:58:33.041133+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.01721","citing_title":"Soft Self-labeling and Potts Relaxations for Weakly-Supervised Segmentation","ref_index":43,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C7MZAHK6AEBXL3TQG3GWHLCF6K","json":"https://pith.science/pith/C7MZAHK6AEBXL3TQG3GWHLCF6K.json","graph_json":"https://pith.science/api/pith-number/C7MZAHK6AEBXL3TQG3GWHLCF6K/graph.json","events_json":"https://pith.science/api/pith-number/C7MZAHK6AEBXL3TQG3GWHLCF6K/events.json","paper":"https://pith.science/paper/C7MZAHK6"},"agent_actions":{"view_html":"https://pith.science/pith/C7MZAHK6AEBXL3TQG3GWHLCF6K","download_json":"https://pith.science/pith/C7MZAHK6AEBXL3TQG3GWHLCF6K.json","view_paper":"https://pith.science/paper/C7MZAHK6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.13225&json=true","fetch_graph":"https://pith.science/api/pith-number/C7MZAHK6AEBXL3TQG3GWHLCF6K/graph.json","fetch_events":"https://pith.science/api/pith-number/C7MZAHK6AEBXL3TQG3GWHLCF6K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C7MZAHK6AEBXL3TQG3GWHLCF6K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C7MZAHK6AEBXL3TQG3GWHLCF6K/action/storage_attestation","attest_author":"https://pith.science/pith/C7MZAHK6AEBXL3TQG3GWHLCF6K/action/author_attestation","sign_citation":"https://pith.science/pith/C7MZAHK6AEBXL3TQG3GWHLCF6K/action/citation_signature","submit_replication":"https://pith.science/pith/C7MZAHK6AEBXL3TQG3GWHLCF6K/action/replication_record"}},"created_at":"2026-07-05T07:58:33.041133+00:00","updated_at":"2026-07-05T07:58:33.041133+00:00"}