{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:RQR2UZMXUMSF67IC56GTD4BHFU","short_pith_number":"pith:RQR2UZMX","schema_version":"1.0","canonical_sha256":"8c23aa6597a3245f7d02ef8d31f0272d2ed91065027e24321fa5d0c4eeb4f9bf","source":{"kind":"arxiv","id":"1803.10464","version":2},"attestation_state":"computed","paper":{"title":"Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiwoon Ahn, Suha Kwak","submitted_at":"2018-03-28T08:40:54Z","abstract_excerpt":"The deficiency of segmentation labels is one of the main obstacles to semantic segmentation in the wild. To alleviate this issue, we present a novel framework that generates segmentation labels of images given their image-level class labels. In this weakly supervised setting, trained models have been known to segment local discriminative parts rather than the entire object area. Our solution is to propagate such local responses to nearby areas which belong to the same semantic entity. To this end, we propose a Deep Neural Network (DNN) called AffinityNet that predicts semantic affinity between"},"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":"1803.10464","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-28T08:40:54Z","cross_cats_sorted":[],"title_canon_sha256":"cad67476335e5ba8a33fbd61ec792caaba60e42df3272be646bfb23e68298f8b","abstract_canon_sha256":"c8bdcffd55e105c93f0ac5283d638ff124e44e73005b2706cb23efe52b75e634"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:19:02.045700Z","signature_b64":"GkYvP1DgQMHXq4G/QtdHkqyTGtsac9aVLj8s5uVtqxgc2xOOHjA+8ccfWAy6xk3xrai/BHAkUNW712/EUbH5Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c23aa6597a3245f7d02ef8d31f0272d2ed91065027e24321fa5d0c4eeb4f9bf","last_reissued_at":"2026-05-18T00:19:02.045087Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:19:02.045087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiwoon Ahn, Suha Kwak","submitted_at":"2018-03-28T08:40:54Z","abstract_excerpt":"The deficiency of segmentation labels is one of the main obstacles to semantic segmentation in the wild. To alleviate this issue, we present a novel framework that generates segmentation labels of images given their image-level class labels. In this weakly supervised setting, trained models have been known to segment local discriminative parts rather than the entire object area. Our solution is to propagate such local responses to nearby areas which belong to the same semantic entity. To this end, we propose a Deep Neural Network (DNN) called AffinityNet that predicts semantic affinity between"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.10464","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":""},"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":"1803.10464","created_at":"2026-05-18T00:19:02.045168+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.10464v2","created_at":"2026-05-18T00:19:02.045168+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.10464","created_at":"2026-05-18T00:19:02.045168+00:00"},{"alias_kind":"pith_short_12","alias_value":"RQR2UZMXUMSF","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_16","alias_value":"RQR2UZMXUMSF67IC","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_8","alias_value":"RQR2UZMX","created_at":"2026-05-18T12:32:50.500415+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.21959","citing_title":"Mitigating Spurious Correlations in Weakly Supervised Semantic Segmentation via Cross-architecture Consistency Regularization","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RQR2UZMXUMSF67IC56GTD4BHFU","json":"https://pith.science/pith/RQR2UZMXUMSF67IC56GTD4BHFU.json","graph_json":"https://pith.science/api/pith-number/RQR2UZMXUMSF67IC56GTD4BHFU/graph.json","events_json":"https://pith.science/api/pith-number/RQR2UZMXUMSF67IC56GTD4BHFU/events.json","paper":"https://pith.science/paper/RQR2UZMX"},"agent_actions":{"view_html":"https://pith.science/pith/RQR2UZMXUMSF67IC56GTD4BHFU","download_json":"https://pith.science/pith/RQR2UZMXUMSF67IC56GTD4BHFU.json","view_paper":"https://pith.science/paper/RQR2UZMX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.10464&json=true","fetch_graph":"https://pith.science/api/pith-number/RQR2UZMXUMSF67IC56GTD4BHFU/graph.json","fetch_events":"https://pith.science/api/pith-number/RQR2UZMXUMSF67IC56GTD4BHFU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RQR2UZMXUMSF67IC56GTD4BHFU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RQR2UZMXUMSF67IC56GTD4BHFU/action/storage_attestation","attest_author":"https://pith.science/pith/RQR2UZMXUMSF67IC56GTD4BHFU/action/author_attestation","sign_citation":"https://pith.science/pith/RQR2UZMXUMSF67IC56GTD4BHFU/action/citation_signature","submit_replication":"https://pith.science/pith/RQR2UZMXUMSF67IC56GTD4BHFU/action/replication_record"}},"created_at":"2026-05-18T00:19:02.045168+00:00","updated_at":"2026-05-18T00:19:02.045168+00:00"}