{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:YCSBXXRTQWCFOA4KVCMERD5KJ6","short_pith_number":"pith:YCSBXXRT","schema_version":"1.0","canonical_sha256":"c0a41bde33858457038aa898488faa4fb2912af8e56c30c4bf14ca61e6ba6f72","source":{"kind":"arxiv","id":"1802.00470","version":1},"attestation_state":"computed","paper":{"title":"Learning random-walk label propagation for weakly-supervised semantic segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Manmohan Chandraker, Paul Vernaza","submitted_at":"2018-02-01T19:44:45Z","abstract_excerpt":"Large-scale training for semantic segmentation is challenging due to the expense of obtaining training data for this task relative to other vision tasks. We propose a novel training approach to address this difficulty. Given cheaply-obtained sparse image labelings, we propagate the sparse labels to produce guessed dense labelings. A standard CNN-based segmentation network is trained to mimic these labelings. The label-propagation process is defined via random-walk hitting probabilities, which leads to a differentiable parameterization with uncertainty estimates that are incorporated into our l"},"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":"1802.00470","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-02-01T19:44:45Z","cross_cats_sorted":[],"title_canon_sha256":"cc59661eaadb1b369f0ec0b65ec6b8c853fe318688e88c27c53743be10c65938","abstract_canon_sha256":"fe9f37109f781adf61b8f6f0fad3bc708d10bfc450accc7c51b43f43fed19989"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:24:33.101529Z","signature_b64":"BV1u4MdN0CaRWYe3M78QO69Q5c9q+r1G9ej3M3npOrV/cgj2zJkgtSXmFC+LvyhvIz+Q+LGBseSJNS4iF4XbCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0a41bde33858457038aa898488faa4fb2912af8e56c30c4bf14ca61e6ba6f72","last_reissued_at":"2026-05-18T00:24:33.101110Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:24:33.101110Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning random-walk label propagation for weakly-supervised semantic segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Manmohan Chandraker, Paul Vernaza","submitted_at":"2018-02-01T19:44:45Z","abstract_excerpt":"Large-scale training for semantic segmentation is challenging due to the expense of obtaining training data for this task relative to other vision tasks. We propose a novel training approach to address this difficulty. Given cheaply-obtained sparse image labelings, we propagate the sparse labels to produce guessed dense labelings. A standard CNN-based segmentation network is trained to mimic these labelings. The label-propagation process is defined via random-walk hitting probabilities, which leads to a differentiable parameterization with uncertainty estimates that are incorporated into our l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.00470","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":"1802.00470","created_at":"2026-05-18T00:24:33.101169+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.00470v1","created_at":"2026-05-18T00:24:33.101169+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.00470","created_at":"2026-05-18T00:24:33.101169+00:00"},{"alias_kind":"pith_short_12","alias_value":"YCSBXXRTQWCF","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_16","alias_value":"YCSBXXRTQWCFOA4K","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_8","alias_value":"YCSBXXRT","created_at":"2026-05-18T12:33:04.347982+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/YCSBXXRTQWCFOA4KVCMERD5KJ6","json":"https://pith.science/pith/YCSBXXRTQWCFOA4KVCMERD5KJ6.json","graph_json":"https://pith.science/api/pith-number/YCSBXXRTQWCFOA4KVCMERD5KJ6/graph.json","events_json":"https://pith.science/api/pith-number/YCSBXXRTQWCFOA4KVCMERD5KJ6/events.json","paper":"https://pith.science/paper/YCSBXXRT"},"agent_actions":{"view_html":"https://pith.science/pith/YCSBXXRTQWCFOA4KVCMERD5KJ6","download_json":"https://pith.science/pith/YCSBXXRTQWCFOA4KVCMERD5KJ6.json","view_paper":"https://pith.science/paper/YCSBXXRT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.00470&json=true","fetch_graph":"https://pith.science/api/pith-number/YCSBXXRTQWCFOA4KVCMERD5KJ6/graph.json","fetch_events":"https://pith.science/api/pith-number/YCSBXXRTQWCFOA4KVCMERD5KJ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YCSBXXRTQWCFOA4KVCMERD5KJ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YCSBXXRTQWCFOA4KVCMERD5KJ6/action/storage_attestation","attest_author":"https://pith.science/pith/YCSBXXRTQWCFOA4KVCMERD5KJ6/action/author_attestation","sign_citation":"https://pith.science/pith/YCSBXXRTQWCFOA4KVCMERD5KJ6/action/citation_signature","submit_replication":"https://pith.science/pith/YCSBXXRTQWCFOA4KVCMERD5KJ6/action/replication_record"}},"created_at":"2026-05-18T00:24:33.101169+00:00","updated_at":"2026-05-18T00:24:33.101169+00:00"}