{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:YDLQ5T5MP3HQRLFJRESKMLRNZN","short_pith_number":"pith:YDLQ5T5M","schema_version":"1.0","canonical_sha256":"c0d70ecfac7ecf08aca98924a62e2dcb515e25dca72218fb41f8f3eb0d61ff0d","source":{"kind":"arxiv","id":"1506.03648","version":2},"attestation_state":"computed","paper":{"title":"Constrained Convolutional Neural Networks for Weakly Supervised Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Deepak Pathak, Philipp Kr\\\"ahenb\\\"uhl, Trevor Darrell","submitted_at":"2015-06-11T12:30:17Z","abstract_excerpt":"We present an approach to learn a dense pixel-wise labeling from image-level tags. Each image-level tag imposes constraints on the output labeling of a Convolutional Neural Network (CNN) classifier. We propose Constrained CNN (CCNN), a method which uses a novel loss function to optimize for any set of linear constraints on the output space (i.e. predicted label distribution) of a CNN. Our loss formulation is easy to optimize and can be incorporated directly into standard stochastic gradient descent optimization. The key idea is to phrase the training objective as a biconvex optimization for li"},"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":"1506.03648","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-06-11T12:30:17Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8c60c8e0b8e0f7c5a74c176fafc02a9e052be719a79fe2016071688d98c8cb34","abstract_canon_sha256":"c55607cd1533c5489be245964b4fe38156aecfbcc9355c7752dbbbdefeba2d25"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:29:54.035528Z","signature_b64":"QoUBSEedJKhuSuWRYnbvFyGHLKtyY2e/djsohPjV73fScvr2uWDz7dPCTRc43gs4gf5GAFkUlBLs4b2vrlaDCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0d70ecfac7ecf08aca98924a62e2dcb515e25dca72218fb41f8f3eb0d61ff0d","last_reissued_at":"2026-05-18T01:29:54.034973Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:29:54.034973Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Constrained Convolutional Neural Networks for Weakly Supervised Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Deepak Pathak, Philipp Kr\\\"ahenb\\\"uhl, Trevor Darrell","submitted_at":"2015-06-11T12:30:17Z","abstract_excerpt":"We present an approach to learn a dense pixel-wise labeling from image-level tags. Each image-level tag imposes constraints on the output labeling of a Convolutional Neural Network (CNN) classifier. We propose Constrained CNN (CCNN), a method which uses a novel loss function to optimize for any set of linear constraints on the output space (i.e. predicted label distribution) of a CNN. Our loss formulation is easy to optimize and can be incorporated directly into standard stochastic gradient descent optimization. The key idea is to phrase the training objective as a biconvex optimization for li"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.03648","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":"1506.03648","created_at":"2026-05-18T01:29:54.035042+00:00"},{"alias_kind":"arxiv_version","alias_value":"1506.03648v2","created_at":"2026-05-18T01:29:54.035042+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.03648","created_at":"2026-05-18T01:29:54.035042+00:00"},{"alias_kind":"pith_short_12","alias_value":"YDLQ5T5MP3HQ","created_at":"2026-05-18T12:29:50.041715+00:00"},{"alias_kind":"pith_short_16","alias_value":"YDLQ5T5MP3HQRLFJ","created_at":"2026-05-18T12:29:50.041715+00:00"},{"alias_kind":"pith_short_8","alias_value":"YDLQ5T5M","created_at":"2026-05-18T12:29:50.041715+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/YDLQ5T5MP3HQRLFJRESKMLRNZN","json":"https://pith.science/pith/YDLQ5T5MP3HQRLFJRESKMLRNZN.json","graph_json":"https://pith.science/api/pith-number/YDLQ5T5MP3HQRLFJRESKMLRNZN/graph.json","events_json":"https://pith.science/api/pith-number/YDLQ5T5MP3HQRLFJRESKMLRNZN/events.json","paper":"https://pith.science/paper/YDLQ5T5M"},"agent_actions":{"view_html":"https://pith.science/pith/YDLQ5T5MP3HQRLFJRESKMLRNZN","download_json":"https://pith.science/pith/YDLQ5T5MP3HQRLFJRESKMLRNZN.json","view_paper":"https://pith.science/paper/YDLQ5T5M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1506.03648&json=true","fetch_graph":"https://pith.science/api/pith-number/YDLQ5T5MP3HQRLFJRESKMLRNZN/graph.json","fetch_events":"https://pith.science/api/pith-number/YDLQ5T5MP3HQRLFJRESKMLRNZN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YDLQ5T5MP3HQRLFJRESKMLRNZN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YDLQ5T5MP3HQRLFJRESKMLRNZN/action/storage_attestation","attest_author":"https://pith.science/pith/YDLQ5T5MP3HQRLFJRESKMLRNZN/action/author_attestation","sign_citation":"https://pith.science/pith/YDLQ5T5MP3HQRLFJRESKMLRNZN/action/citation_signature","submit_replication":"https://pith.science/pith/YDLQ5T5MP3HQRLFJRESKMLRNZN/action/replication_record"}},"created_at":"2026-05-18T01:29:54.035042+00:00","updated_at":"2026-05-18T01:29:54.035042+00:00"}