{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TQ72OHZXHOXSIZOXZHO5X4VOSR","short_pith_number":"pith:TQ72OHZX","schema_version":"1.0","canonical_sha256":"9c3fa71f373baf2465d7c9dddbf2ae945ba85dc6b8fbb288d8962691363d74c8","source":{"kind":"arxiv","id":"2404.12252","version":1},"attestation_state":"computed","paper":{"title":"Deep Gaussian mixture model for unsupervised image segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Agnes Mayr, Markus Haltmeier, Matthias Schwab","submitted_at":"2024-04-18T15:20:59Z","abstract_excerpt":"The recent emergence of deep learning has led to a great deal of work on designing supervised deep semantic segmentation algorithms. As in many tasks sufficient pixel-level labels are very difficult to obtain, we propose a method which combines a Gaussian mixture model (GMM) with unsupervised deep learning techniques. In the standard GMM the pixel values with each sub-region are modelled by a Gaussian distribution. In order to identify the different regions, the parameter vector that minimizes the negative log-likelihood (NLL) function regarding the GMM has to be approximated. For this task, u"},"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":"2404.12252","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-18T15:20:59Z","cross_cats_sorted":[],"title_canon_sha256":"f650092008dc65743b4730a05e62c380d00f53807c414051953af8709f24e184","abstract_canon_sha256":"ab2d0afcea71f7308fffb50da02c4ea2ae003a3afe9e12c6f3e633aa0103c989"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:09:37.589483Z","signature_b64":"OFADiO51nlpKbJQcMvNb3tfrhQ6D1I43zi8UVGqvkMTUjJHdUu4ibRYfBZfnf/2XbkDcQIt9HmaJZn0SYusmAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c3fa71f373baf2465d7c9dddbf2ae945ba85dc6b8fbb288d8962691363d74c8","last_reissued_at":"2026-07-05T08:09:37.589069Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:09:37.589069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Gaussian mixture model for unsupervised image segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Agnes Mayr, Markus Haltmeier, Matthias Schwab","submitted_at":"2024-04-18T15:20:59Z","abstract_excerpt":"The recent emergence of deep learning has led to a great deal of work on designing supervised deep semantic segmentation algorithms. As in many tasks sufficient pixel-level labels are very difficult to obtain, we propose a method which combines a Gaussian mixture model (GMM) with unsupervised deep learning techniques. In the standard GMM the pixel values with each sub-region are modelled by a Gaussian distribution. In order to identify the different regions, the parameter vector that minimizes the negative log-likelihood (NLL) function regarding the GMM has to be approximated. For this task, u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.12252","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2404.12252/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2404.12252","created_at":"2026-07-05T08:09:37.589129+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.12252v1","created_at":"2026-07-05T08:09:37.589129+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.12252","created_at":"2026-07-05T08:09:37.589129+00:00"},{"alias_kind":"pith_short_12","alias_value":"TQ72OHZXHOXS","created_at":"2026-07-05T08:09:37.589129+00:00"},{"alias_kind":"pith_short_16","alias_value":"TQ72OHZXHOXSIZOX","created_at":"2026-07-05T08:09:37.589129+00:00"},{"alias_kind":"pith_short_8","alias_value":"TQ72OHZX","created_at":"2026-07-05T08:09:37.589129+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.15086","citing_title":"Quantum-enhanced unsupervised image segmentation for medical images analysis","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TQ72OHZXHOXSIZOXZHO5X4VOSR","json":"https://pith.science/pith/TQ72OHZXHOXSIZOXZHO5X4VOSR.json","graph_json":"https://pith.science/api/pith-number/TQ72OHZXHOXSIZOXZHO5X4VOSR/graph.json","events_json":"https://pith.science/api/pith-number/TQ72OHZXHOXSIZOXZHO5X4VOSR/events.json","paper":"https://pith.science/paper/TQ72OHZX"},"agent_actions":{"view_html":"https://pith.science/pith/TQ72OHZXHOXSIZOXZHO5X4VOSR","download_json":"https://pith.science/pith/TQ72OHZXHOXSIZOXZHO5X4VOSR.json","view_paper":"https://pith.science/paper/TQ72OHZX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.12252&json=true","fetch_graph":"https://pith.science/api/pith-number/TQ72OHZXHOXSIZOXZHO5X4VOSR/graph.json","fetch_events":"https://pith.science/api/pith-number/TQ72OHZXHOXSIZOXZHO5X4VOSR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TQ72OHZXHOXSIZOXZHO5X4VOSR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TQ72OHZXHOXSIZOXZHO5X4VOSR/action/storage_attestation","attest_author":"https://pith.science/pith/TQ72OHZXHOXSIZOXZHO5X4VOSR/action/author_attestation","sign_citation":"https://pith.science/pith/TQ72OHZXHOXSIZOXZHO5X4VOSR/action/citation_signature","submit_replication":"https://pith.science/pith/TQ72OHZXHOXSIZOXZHO5X4VOSR/action/replication_record"}},"created_at":"2026-07-05T08:09:37.589129+00:00","updated_at":"2026-07-05T08:09:37.589129+00:00"}