{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NCALJ27DSZKL6TWU677TEUDC6T","short_pith_number":"pith:NCALJ27D","schema_version":"1.0","canonical_sha256":"6880b4ebe39654bf4ed4f7ff325062f4cfc761832e2a2e2b9f6ed2e1b25ce0a8","source":{"kind":"arxiv","id":"2404.08195","version":1},"attestation_state":"computed","paper":{"title":"Tackling Ambiguity from Perspective of Uncertainty Inference and Affinity Diversification for Weakly Supervised Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kexue Fu, Shuo Wang, Yucong Meng, Zhijian Song, Zhiwei Yang","submitted_at":"2024-04-12T01:54:59Z","abstract_excerpt":"Weakly supervised semantic segmentation (WSSS) with image-level labels intends to achieve dense tasks without laborious annotations. However, due to the ambiguous contexts and fuzzy regions, the performance of WSSS, especially the stages of generating Class Activation Maps (CAMs) and refining pseudo masks, widely suffers from ambiguity while being barely noticed by previous literature. In this work, we propose UniA, a unified single-staged WSSS framework, to efficiently tackle this issue from the perspective of uncertainty inference and affinity diversification, respectively. When activating c"},"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":"2404.08195","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-12T01:54:59Z","cross_cats_sorted":[],"title_canon_sha256":"6e01b870e8e6a9a7036983cd529daf43bfdb5060a0cfa9faa5e059097bb3b201","abstract_canon_sha256":"33b1ab78673e7943297a2e76fbf858ae2981b54ebe06a32f1f873797e85a6ce2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:07:19.104086Z","signature_b64":"9xT03OUMc3AQP6TLI5+qrBkv/1vxldtXoy7v73fqXmPk40TyxxwCEUQrKStA1uUIwJVG1AtB/tQGyQlema9FCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6880b4ebe39654bf4ed4f7ff325062f4cfc761832e2a2e2b9f6ed2e1b25ce0a8","last_reissued_at":"2026-07-05T08:07:19.103688Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:07:19.103688Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tackling Ambiguity from Perspective of Uncertainty Inference and Affinity Diversification for Weakly Supervised Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kexue Fu, Shuo Wang, Yucong Meng, Zhijian Song, Zhiwei Yang","submitted_at":"2024-04-12T01:54:59Z","abstract_excerpt":"Weakly supervised semantic segmentation (WSSS) with image-level labels intends to achieve dense tasks without laborious annotations. However, due to the ambiguous contexts and fuzzy regions, the performance of WSSS, especially the stages of generating Class Activation Maps (CAMs) and refining pseudo masks, widely suffers from ambiguity while being barely noticed by previous literature. In this work, we propose UniA, a unified single-staged WSSS framework, to efficiently tackle this issue from the perspective of uncertainty inference and affinity diversification, respectively. When activating c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.08195","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/2404.08195/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":"2404.08195","created_at":"2026-07-05T08:07:19.103742+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.08195v1","created_at":"2026-07-05T08:07:19.103742+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.08195","created_at":"2026-07-05T08:07:19.103742+00:00"},{"alias_kind":"pith_short_12","alias_value":"NCALJ27DSZKL","created_at":"2026-07-05T08:07:19.103742+00:00"},{"alias_kind":"pith_short_16","alias_value":"NCALJ27DSZKL6TWU","created_at":"2026-07-05T08:07:19.103742+00:00"},{"alias_kind":"pith_short_8","alias_value":"NCALJ27D","created_at":"2026-07-05T08:07:19.103742+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.04593","citing_title":"DiCLIP: Diffusion Model Enhances CLIP's Dense Knowledge for Weakly Supervised Semantic Segmentation","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NCALJ27DSZKL6TWU677TEUDC6T","json":"https://pith.science/pith/NCALJ27DSZKL6TWU677TEUDC6T.json","graph_json":"https://pith.science/api/pith-number/NCALJ27DSZKL6TWU677TEUDC6T/graph.json","events_json":"https://pith.science/api/pith-number/NCALJ27DSZKL6TWU677TEUDC6T/events.json","paper":"https://pith.science/paper/NCALJ27D"},"agent_actions":{"view_html":"https://pith.science/pith/NCALJ27DSZKL6TWU677TEUDC6T","download_json":"https://pith.science/pith/NCALJ27DSZKL6TWU677TEUDC6T.json","view_paper":"https://pith.science/paper/NCALJ27D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.08195&json=true","fetch_graph":"https://pith.science/api/pith-number/NCALJ27DSZKL6TWU677TEUDC6T/graph.json","fetch_events":"https://pith.science/api/pith-number/NCALJ27DSZKL6TWU677TEUDC6T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NCALJ27DSZKL6TWU677TEUDC6T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NCALJ27DSZKL6TWU677TEUDC6T/action/storage_attestation","attest_author":"https://pith.science/pith/NCALJ27DSZKL6TWU677TEUDC6T/action/author_attestation","sign_citation":"https://pith.science/pith/NCALJ27DSZKL6TWU677TEUDC6T/action/citation_signature","submit_replication":"https://pith.science/pith/NCALJ27DSZKL6TWU677TEUDC6T/action/replication_record"}},"created_at":"2026-07-05T08:07:19.103742+00:00","updated_at":"2026-07-05T08:07:19.103742+00:00"}