{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:ACJZSEZJYA7NSH544I4JV6AGVZ","short_pith_number":"pith:ACJZSEZJ","schema_version":"1.0","canonical_sha256":"0093991329c03ed91fbce2389af806ae5f0bc0c4d013e30e71dec6ca6973ed34","source":{"kind":"arxiv","id":"1810.07050","version":1},"attestation_state":"computed","paper":{"title":"Generating Self-Guided Dense Annotations for Weakly Supervised Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chiou-Ting Hsu, Zi-Yi Ke","submitted_at":"2018-10-16T14:49:18Z","abstract_excerpt":"Learning semantic segmentation models under image-level supervision is far more challenging than under fully supervised setting. Without knowing the exact pixel-label correspondence, most weakly-supervised methods rely on external models to infer pseudo pixel-level labels for training semantic segmentation models. In this paper, we aim to develop a single neural network without resorting to any external models. We propose a novel self-guided strategy to fully utilize features learned across multiple levels to progressively generate the dense pseudo labels. First, we use high-level features as "},"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":"1810.07050","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-10-16T14:49:18Z","cross_cats_sorted":[],"title_canon_sha256":"27b415a36fa61974ee20d0e560d477547425d6aba6a7ad798f28094b7076713d","abstract_canon_sha256":"b4b3dd95374725015631320337de281ea1dbac3e50fdadd4120395d9cb748866"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:03:10.622471Z","signature_b64":"li4xmVZOAuoGKc+kXknCPApSTzBIQ2QqES06MzzJVr7EmB6JSzqQq5H9qKnnjxFJJ3PAcx6+wAZAJpwjDS3cCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0093991329c03ed91fbce2389af806ae5f0bc0c4d013e30e71dec6ca6973ed34","last_reissued_at":"2026-05-18T00:03:10.621775Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:03:10.621775Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generating Self-Guided Dense Annotations for Weakly Supervised Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chiou-Ting Hsu, Zi-Yi Ke","submitted_at":"2018-10-16T14:49:18Z","abstract_excerpt":"Learning semantic segmentation models under image-level supervision is far more challenging than under fully supervised setting. Without knowing the exact pixel-label correspondence, most weakly-supervised methods rely on external models to infer pseudo pixel-level labels for training semantic segmentation models. In this paper, we aim to develop a single neural network without resorting to any external models. We propose a novel self-guided strategy to fully utilize features learned across multiple levels to progressively generate the dense pseudo labels. First, we use high-level features as "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.07050","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":""},"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":"1810.07050","created_at":"2026-05-18T00:03:10.621879+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.07050v1","created_at":"2026-05-18T00:03:10.621879+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.07050","created_at":"2026-05-18T00:03:10.621879+00:00"},{"alias_kind":"pith_short_12","alias_value":"ACJZSEZJYA7N","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_16","alias_value":"ACJZSEZJYA7NSH54","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_8","alias_value":"ACJZSEZJ","created_at":"2026-05-18T12:32:13.499390+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/ACJZSEZJYA7NSH544I4JV6AGVZ","json":"https://pith.science/pith/ACJZSEZJYA7NSH544I4JV6AGVZ.json","graph_json":"https://pith.science/api/pith-number/ACJZSEZJYA7NSH544I4JV6AGVZ/graph.json","events_json":"https://pith.science/api/pith-number/ACJZSEZJYA7NSH544I4JV6AGVZ/events.json","paper":"https://pith.science/paper/ACJZSEZJ"},"agent_actions":{"view_html":"https://pith.science/pith/ACJZSEZJYA7NSH544I4JV6AGVZ","download_json":"https://pith.science/pith/ACJZSEZJYA7NSH544I4JV6AGVZ.json","view_paper":"https://pith.science/paper/ACJZSEZJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.07050&json=true","fetch_graph":"https://pith.science/api/pith-number/ACJZSEZJYA7NSH544I4JV6AGVZ/graph.json","fetch_events":"https://pith.science/api/pith-number/ACJZSEZJYA7NSH544I4JV6AGVZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ACJZSEZJYA7NSH544I4JV6AGVZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ACJZSEZJYA7NSH544I4JV6AGVZ/action/storage_attestation","attest_author":"https://pith.science/pith/ACJZSEZJYA7NSH544I4JV6AGVZ/action/author_attestation","sign_citation":"https://pith.science/pith/ACJZSEZJYA7NSH544I4JV6AGVZ/action/citation_signature","submit_replication":"https://pith.science/pith/ACJZSEZJYA7NSH544I4JV6AGVZ/action/replication_record"}},"created_at":"2026-05-18T00:03:10.621879+00:00","updated_at":"2026-05-18T00:03:10.621879+00:00"}