{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:TNAFYV2WPUV23DG7DOGTDDIUX4","short_pith_number":"pith:TNAFYV2W","schema_version":"1.0","canonical_sha256":"9b405c57567d2bad8cdf1b8d318d14bf1d8e929a01b769ab2b1f53fa3588816e","source":{"kind":"arxiv","id":"1603.07485","version":2},"attestation_state":"computed","paper":{"title":"Simple Does It: Weakly Supervised Instance and Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anna Khoreva, Bernt Schiele, Jan Hosang, Matthias Hein, Rodrigo Benenson","submitted_at":"2016-03-24T09:04:16Z","abstract_excerpt":"Semantic labelling and instance segmentation are two tasks that require particularly costly annotations. Starting from weak supervision in the form of bounding box detection annotations, we propose a new approach that does not require modification of the segmentation training procedure. We show that when carefully designing the input labels from given bounding boxes, even a single round of training is enough to improve over previously reported weakly supervised results. Overall, our weak supervision approach reaches ~95% of the quality of the fully supervised model, both for semantic labelling"},"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":"1603.07485","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-03-24T09:04:16Z","cross_cats_sorted":[],"title_canon_sha256":"7f9186afe02478ebe48cf195854f2d0a7c6892adcf752e26f6eccba5d9f574c0","abstract_canon_sha256":"f97fe88d1af024fc0a9ea5a4dc618526e9f0d64fedad3e1728588abea9f1fe9a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:57:04.639362Z","signature_b64":"vL07yuc5m7vwdqVxPKbwqhCBGvkSQZXyXQIe2Mg45uO3samW9S99ITFNH3XdudLYw/fVuEAE/ESzQl8W3fkVCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b405c57567d2bad8cdf1b8d318d14bf1d8e929a01b769ab2b1f53fa3588816e","last_reissued_at":"2026-05-18T00:57:04.638507Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:57:04.638507Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Simple Does It: Weakly Supervised Instance and Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anna Khoreva, Bernt Schiele, Jan Hosang, Matthias Hein, Rodrigo Benenson","submitted_at":"2016-03-24T09:04:16Z","abstract_excerpt":"Semantic labelling and instance segmentation are two tasks that require particularly costly annotations. Starting from weak supervision in the form of bounding box detection annotations, we propose a new approach that does not require modification of the segmentation training procedure. We show that when carefully designing the input labels from given bounding boxes, even a single round of training is enough to improve over previously reported weakly supervised results. Overall, our weak supervision approach reaches ~95% of the quality of the fully supervised model, both for semantic labelling"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.07485","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":"1603.07485","created_at":"2026-05-18T00:57:04.638654+00:00"},{"alias_kind":"arxiv_version","alias_value":"1603.07485v2","created_at":"2026-05-18T00:57:04.638654+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.07485","created_at":"2026-05-18T00:57:04.638654+00:00"},{"alias_kind":"pith_short_12","alias_value":"TNAFYV2WPUV2","created_at":"2026-05-18T12:30:44.179134+00:00"},{"alias_kind":"pith_short_16","alias_value":"TNAFYV2WPUV23DG7","created_at":"2026-05-18T12:30:44.179134+00:00"},{"alias_kind":"pith_short_8","alias_value":"TNAFYV2W","created_at":"2026-05-18T12:30:44.179134+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.03954","citing_title":"Signet Ring Cell Detection With a Semi-supervised Learning Framework","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TNAFYV2WPUV23DG7DOGTDDIUX4","json":"https://pith.science/pith/TNAFYV2WPUV23DG7DOGTDDIUX4.json","graph_json":"https://pith.science/api/pith-number/TNAFYV2WPUV23DG7DOGTDDIUX4/graph.json","events_json":"https://pith.science/api/pith-number/TNAFYV2WPUV23DG7DOGTDDIUX4/events.json","paper":"https://pith.science/paper/TNAFYV2W"},"agent_actions":{"view_html":"https://pith.science/pith/TNAFYV2WPUV23DG7DOGTDDIUX4","download_json":"https://pith.science/pith/TNAFYV2WPUV23DG7DOGTDDIUX4.json","view_paper":"https://pith.science/paper/TNAFYV2W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1603.07485&json=true","fetch_graph":"https://pith.science/api/pith-number/TNAFYV2WPUV23DG7DOGTDDIUX4/graph.json","fetch_events":"https://pith.science/api/pith-number/TNAFYV2WPUV23DG7DOGTDDIUX4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TNAFYV2WPUV23DG7DOGTDDIUX4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TNAFYV2WPUV23DG7DOGTDDIUX4/action/storage_attestation","attest_author":"https://pith.science/pith/TNAFYV2WPUV23DG7DOGTDDIUX4/action/author_attestation","sign_citation":"https://pith.science/pith/TNAFYV2WPUV23DG7DOGTDDIUX4/action/citation_signature","submit_replication":"https://pith.science/pith/TNAFYV2WPUV23DG7DOGTDDIUX4/action/replication_record"}},"created_at":"2026-05-18T00:57:04.638654+00:00","updated_at":"2026-05-18T00:57:04.638654+00:00"}