{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:2MSXKVV5CFULURQJJ43R5XOD5I","short_pith_number":"pith:2MSXKVV5","schema_version":"1.0","canonical_sha256":"d3257556bd1168ba46094f371eddc3ea149c18aedcb9632d8f27a7b560fc3d35","source":{"kind":"arxiv","id":"2203.02664","version":2},"attestation_state":"computed","paper":{"title":"Learning Affinity from Attention: End-to-End Weakly-Supervised Semantic Segmentation with Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baosheng Yu, Bo Du, Lixiang Ru, Yibing Zhan","submitted_at":"2022-03-05T06:07:17Z","abstract_excerpt":"Weakly-supervised semantic segmentation (WSSS) with image-level labels is an important and challenging task. Due to the high training efficiency, end-to-end solutions for WSSS have received increasing attention from the community. However, current methods are mainly based on convolutional neural networks and fail to explore the global information properly, thus usually resulting in incomplete object regions. In this paper, to address the aforementioned problem, we introduce Transformers, which naturally integrate global information, to generate more integral initial pseudo labels for end-to-en"},"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":"2203.02664","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-05T06:07:17Z","cross_cats_sorted":[],"title_canon_sha256":"179d96f918c9167055e2bd11dd92619c62fd64b502affbbebcb418224949e64a","abstract_canon_sha256":"a04a9f861287da49b26da4f2771bc75fbf32de1bd81336ce9cd3ad24e558d6c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:55:38.256768Z","signature_b64":"vMPIl2w29sGT5kYzlETB88gdodyFz7YTJN288uLTcx0Glcn7Whw/+IfLFdba59LDZXKwGRVXp8G3frTSW5tWAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3257556bd1168ba46094f371eddc3ea149c18aedcb9632d8f27a7b560fc3d35","last_reissued_at":"2026-07-05T04:55:38.256282Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:55:38.256282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Affinity from Attention: End-to-End Weakly-Supervised Semantic Segmentation with Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baosheng Yu, Bo Du, Lixiang Ru, Yibing Zhan","submitted_at":"2022-03-05T06:07:17Z","abstract_excerpt":"Weakly-supervised semantic segmentation (WSSS) with image-level labels is an important and challenging task. Due to the high training efficiency, end-to-end solutions for WSSS have received increasing attention from the community. However, current methods are mainly based on convolutional neural networks and fail to explore the global information properly, thus usually resulting in incomplete object regions. In this paper, to address the aforementioned problem, we introduce Transformers, which naturally integrate global information, to generate more integral initial pseudo labels for end-to-en"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.02664","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/2203.02664/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":"2203.02664","created_at":"2026-07-05T04:55:38.256342+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.02664v2","created_at":"2026-07-05T04:55:38.256342+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.02664","created_at":"2026-07-05T04:55:38.256342+00:00"},{"alias_kind":"pith_short_12","alias_value":"2MSXKVV5CFUL","created_at":"2026-07-05T04:55:38.256342+00:00"},{"alias_kind":"pith_short_16","alias_value":"2MSXKVV5CFULURQJ","created_at":"2026-07-05T04:55:38.256342+00:00"},{"alias_kind":"pith_short_8","alias_value":"2MSXKVV5","created_at":"2026-07-05T04:55:38.256342+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.11765","citing_title":"ProBAG: Prototype-Guided Boundary-Aware Graph Diffusion for Weakly Supervised Histopathology Segmentation","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2MSXKVV5CFULURQJJ43R5XOD5I","json":"https://pith.science/pith/2MSXKVV5CFULURQJJ43R5XOD5I.json","graph_json":"https://pith.science/api/pith-number/2MSXKVV5CFULURQJJ43R5XOD5I/graph.json","events_json":"https://pith.science/api/pith-number/2MSXKVV5CFULURQJJ43R5XOD5I/events.json","paper":"https://pith.science/paper/2MSXKVV5"},"agent_actions":{"view_html":"https://pith.science/pith/2MSXKVV5CFULURQJJ43R5XOD5I","download_json":"https://pith.science/pith/2MSXKVV5CFULURQJJ43R5XOD5I.json","view_paper":"https://pith.science/paper/2MSXKVV5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.02664&json=true","fetch_graph":"https://pith.science/api/pith-number/2MSXKVV5CFULURQJJ43R5XOD5I/graph.json","fetch_events":"https://pith.science/api/pith-number/2MSXKVV5CFULURQJJ43R5XOD5I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2MSXKVV5CFULURQJJ43R5XOD5I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2MSXKVV5CFULURQJJ43R5XOD5I/action/storage_attestation","attest_author":"https://pith.science/pith/2MSXKVV5CFULURQJJ43R5XOD5I/action/author_attestation","sign_citation":"https://pith.science/pith/2MSXKVV5CFULURQJJ43R5XOD5I/action/citation_signature","submit_replication":"https://pith.science/pith/2MSXKVV5CFULURQJJ43R5XOD5I/action/replication_record"}},"created_at":"2026-07-05T04:55:38.256342+00:00","updated_at":"2026-07-05T04:55:38.256342+00:00"}