{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:Z64TVBR7RK2XQ7OFSZTQNBC6JZ","short_pith_number":"pith:Z64TVBR7","schema_version":"1.0","canonical_sha256":"cfb93a863f8ab5787dc5966706845e4e7808ac5b9ed63be78646f7abbc9b75c7","source":{"kind":"arxiv","id":"2108.12995","version":2},"attestation_state":"computed","paper":{"title":"Pseudo-mask Matters in Weakly-supervised Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Liyang Liu, Wayne Zhang, Yi Li, Yimin Chen, Zhanghui Kuang","submitted_at":"2021-08-30T05:35:28Z","abstract_excerpt":"Most weakly supervised semantic segmentation (WSSS) methods follow the pipeline that generates pseudo-masks initially and trains the segmentation model with the pseudo-masks in fully supervised manner after. However, we find some matters related to the pseudo-masks, including high quality pseudo-masks generation from class activation maps (CAMs), and training with noisy pseudo-mask supervision. For these matters, we propose the following designs to push the performance to new state-of-art: (i) Coefficient of Variation Smoothing to smooth the CAMs adaptively; (ii) Proportional Pseudo-mask Gener"},"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":"2108.12995","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-08-30T05:35:28Z","cross_cats_sorted":[],"title_canon_sha256":"4bdf0306b4d568bd038ca580e09ff0b84e3b59413a878b173ff9ac9598fa3f51","abstract_canon_sha256":"977c86a3df9ec4edb32fe216f284150b8e5bc668639d4b247541f4f616a3c9c6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:12:16.503390Z","signature_b64":"QYg/au2Rdzjg/MxP/NhTos5cDQDduS6L6FOqTl082JRvILehvR7HqQLBWQPfU8KyQw1oXha23WEF9ytiJXUeDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cfb93a863f8ab5787dc5966706845e4e7808ac5b9ed63be78646f7abbc9b75c7","last_reissued_at":"2026-07-05T03:12:16.502985Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:12:16.502985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pseudo-mask Matters in Weakly-supervised Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Liyang Liu, Wayne Zhang, Yi Li, Yimin Chen, Zhanghui Kuang","submitted_at":"2021-08-30T05:35:28Z","abstract_excerpt":"Most weakly supervised semantic segmentation (WSSS) methods follow the pipeline that generates pseudo-masks initially and trains the segmentation model with the pseudo-masks in fully supervised manner after. However, we find some matters related to the pseudo-masks, including high quality pseudo-masks generation from class activation maps (CAMs), and training with noisy pseudo-mask supervision. For these matters, we propose the following designs to push the performance to new state-of-art: (i) Coefficient of Variation Smoothing to smooth the CAMs adaptively; (ii) Proportional Pseudo-mask Gener"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.12995","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/2108.12995/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":"2108.12995","created_at":"2026-07-05T03:12:16.503047+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.12995v2","created_at":"2026-07-05T03:12:16.503047+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.12995","created_at":"2026-07-05T03:12:16.503047+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z64TVBR7RK2X","created_at":"2026-07-05T03:12:16.503047+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z64TVBR7RK2XQ7OF","created_at":"2026-07-05T03:12:16.503047+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z64TVBR7","created_at":"2026-07-05T03:12:16.503047+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/Z64TVBR7RK2XQ7OFSZTQNBC6JZ","json":"https://pith.science/pith/Z64TVBR7RK2XQ7OFSZTQNBC6JZ.json","graph_json":"https://pith.science/api/pith-number/Z64TVBR7RK2XQ7OFSZTQNBC6JZ/graph.json","events_json":"https://pith.science/api/pith-number/Z64TVBR7RK2XQ7OFSZTQNBC6JZ/events.json","paper":"https://pith.science/paper/Z64TVBR7"},"agent_actions":{"view_html":"https://pith.science/pith/Z64TVBR7RK2XQ7OFSZTQNBC6JZ","download_json":"https://pith.science/pith/Z64TVBR7RK2XQ7OFSZTQNBC6JZ.json","view_paper":"https://pith.science/paper/Z64TVBR7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.12995&json=true","fetch_graph":"https://pith.science/api/pith-number/Z64TVBR7RK2XQ7OFSZTQNBC6JZ/graph.json","fetch_events":"https://pith.science/api/pith-number/Z64TVBR7RK2XQ7OFSZTQNBC6JZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z64TVBR7RK2XQ7OFSZTQNBC6JZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z64TVBR7RK2XQ7OFSZTQNBC6JZ/action/storage_attestation","attest_author":"https://pith.science/pith/Z64TVBR7RK2XQ7OFSZTQNBC6JZ/action/author_attestation","sign_citation":"https://pith.science/pith/Z64TVBR7RK2XQ7OFSZTQNBC6JZ/action/citation_signature","submit_replication":"https://pith.science/pith/Z64TVBR7RK2XQ7OFSZTQNBC6JZ/action/replication_record"}},"created_at":"2026-07-05T03:12:16.503047+00:00","updated_at":"2026-07-05T03:12:16.503047+00:00"}