{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:ZQXLS3JBKKZTATZ2AWBVJYGZAB","short_pith_number":"pith:ZQXLS3JB","schema_version":"1.0","canonical_sha256":"cc2eb96d2152b3304f3a058354e0d9004328bf634c374ad25e37a3078320e60e","source":{"kind":"arxiv","id":"1502.02734","version":3},"attestation_state":"computed","paper":{"title":"Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alan L. Yuille, George Papandreou, Kevin Murphy, Liang-Chieh Chen","submitted_at":"2015-02-09T23:38:45Z","abstract_excerpt":"Deep convolutional neural networks (DCNNs) trained on a large number of images with strong pixel-level annotations have recently significantly pushed the state-of-art in semantic image segmentation. We study the more challenging problem of learning DCNNs for semantic image segmentation from either (1) weakly annotated training data such as bounding boxes or image-level labels or (2) a combination of few strongly labeled and many weakly labeled images, sourced from one or multiple datasets. We develop Expectation-Maximization (EM) methods for semantic image segmentation model training under the"},"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":"1502.02734","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-02-09T23:38:45Z","cross_cats_sorted":[],"title_canon_sha256":"3a8ad704040a444255a0fc30ac615ab01909597d77a7696aeb87e50509097a73","abstract_canon_sha256":"8c98e2877dbed23c9d09aef46fde10ede0519b1ec612dc504cc28703da791841"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:31:03.316194Z","signature_b64":"ODlEAaqW4Up2gj8rJhhDu1FVpWOxIteGNDMPvO+Gx4PjSnzmbAxxP97d2GazQGE9nuh6zNFhON9UaixGC13fCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc2eb96d2152b3304f3a058354e0d9004328bf634c374ad25e37a3078320e60e","last_reissued_at":"2026-05-18T01:31:03.315702Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:31:03.315702Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alan L. Yuille, George Papandreou, Kevin Murphy, Liang-Chieh Chen","submitted_at":"2015-02-09T23:38:45Z","abstract_excerpt":"Deep convolutional neural networks (DCNNs) trained on a large number of images with strong pixel-level annotations have recently significantly pushed the state-of-art in semantic image segmentation. We study the more challenging problem of learning DCNNs for semantic image segmentation from either (1) weakly annotated training data such as bounding boxes or image-level labels or (2) a combination of few strongly labeled and many weakly labeled images, sourced from one or multiple datasets. We develop Expectation-Maximization (EM) methods for semantic image segmentation model training under the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1502.02734","kind":"arxiv","version":3},"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":"1502.02734","created_at":"2026-05-18T01:31:03.315781+00:00"},{"alias_kind":"arxiv_version","alias_value":"1502.02734v3","created_at":"2026-05-18T01:31:03.315781+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1502.02734","created_at":"2026-05-18T01:31:03.315781+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZQXLS3JBKKZT","created_at":"2026-05-18T12:29:52.810259+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZQXLS3JBKKZTATZ2","created_at":"2026-05-18T12:29:52.810259+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZQXLS3JB","created_at":"2026-05-18T12:29:52.810259+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/ZQXLS3JBKKZTATZ2AWBVJYGZAB","json":"https://pith.science/pith/ZQXLS3JBKKZTATZ2AWBVJYGZAB.json","graph_json":"https://pith.science/api/pith-number/ZQXLS3JBKKZTATZ2AWBVJYGZAB/graph.json","events_json":"https://pith.science/api/pith-number/ZQXLS3JBKKZTATZ2AWBVJYGZAB/events.json","paper":"https://pith.science/paper/ZQXLS3JB"},"agent_actions":{"view_html":"https://pith.science/pith/ZQXLS3JBKKZTATZ2AWBVJYGZAB","download_json":"https://pith.science/pith/ZQXLS3JBKKZTATZ2AWBVJYGZAB.json","view_paper":"https://pith.science/paper/ZQXLS3JB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1502.02734&json=true","fetch_graph":"https://pith.science/api/pith-number/ZQXLS3JBKKZTATZ2AWBVJYGZAB/graph.json","fetch_events":"https://pith.science/api/pith-number/ZQXLS3JBKKZTATZ2AWBVJYGZAB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZQXLS3JBKKZTATZ2AWBVJYGZAB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZQXLS3JBKKZTATZ2AWBVJYGZAB/action/storage_attestation","attest_author":"https://pith.science/pith/ZQXLS3JBKKZTATZ2AWBVJYGZAB/action/author_attestation","sign_citation":"https://pith.science/pith/ZQXLS3JBKKZTATZ2AWBVJYGZAB/action/citation_signature","submit_replication":"https://pith.science/pith/ZQXLS3JBKKZTATZ2AWBVJYGZAB/action/replication_record"}},"created_at":"2026-05-18T01:31:03.315781+00:00","updated_at":"2026-05-18T01:31:03.315781+00:00"}