{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:BOQE74QHT3ZRE3E4T2AMES3RL6","short_pith_number":"pith:BOQE74QH","schema_version":"1.0","canonical_sha256":"0ba04ff2079ef3126c9c9e80c24b715f8c30ab4fa33c283a50aa213994c9c30c","source":{"kind":"arxiv","id":"1804.01552","version":1},"attestation_state":"computed","paper":{"title":"Self-supervised Learning of Geometrically Stable Features Through Probabilistic Introspection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea Vedaldi, David Novotny, Diane Larlus, Samuel Albanie","submitted_at":"2018-04-04T18:15:17Z","abstract_excerpt":"Self-supervision can dramatically cut back the amount of manually-labelled data required to train deep neural networks. While self-supervision has usually been considered for tasks such as image classification, in this paper we aim at extending it to geometry-oriented tasks such as semantic matching and part detection. We do so by building on several recent ideas in unsupervised landmark detection. Our approach learns dense distinctive visual descriptors from an unlabelled dataset of images using synthetic image transformations. It does so by means of a robust probabilistic formulation that ca"},"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":"1804.01552","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-04T18:15:17Z","cross_cats_sorted":[],"title_canon_sha256":"c08e6c6427bf33a8bc752c4ae3c2fef2e55f2f82c6dd95cb70477e0dd0a04873","abstract_canon_sha256":"38f96470b17db88c9a8b359a4d0865ffb637a90bf8a40574cbd09fef862c3775"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:19:14.642029Z","signature_b64":"8CBGij0FZj+dYw1u4YZ2eTZz1+hpJ/gCG16OGU7tNLNjdKEi3EkNMY/ZCarVdZtrG1Q+lH46t/1xbDfMPPAVDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ba04ff2079ef3126c9c9e80c24b715f8c30ab4fa33c283a50aa213994c9c30c","last_reissued_at":"2026-05-18T00:19:14.641420Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:19:14.641420Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-supervised Learning of Geometrically Stable Features Through Probabilistic Introspection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea Vedaldi, David Novotny, Diane Larlus, Samuel Albanie","submitted_at":"2018-04-04T18:15:17Z","abstract_excerpt":"Self-supervision can dramatically cut back the amount of manually-labelled data required to train deep neural networks. While self-supervision has usually been considered for tasks such as image classification, in this paper we aim at extending it to geometry-oriented tasks such as semantic matching and part detection. We do so by building on several recent ideas in unsupervised landmark detection. Our approach learns dense distinctive visual descriptors from an unlabelled dataset of images using synthetic image transformations. It does so by means of a robust probabilistic formulation that ca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.01552","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":"1804.01552","created_at":"2026-05-18T00:19:14.641507+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.01552v1","created_at":"2026-05-18T00:19:14.641507+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.01552","created_at":"2026-05-18T00:19:14.641507+00:00"},{"alias_kind":"pith_short_12","alias_value":"BOQE74QHT3ZR","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_16","alias_value":"BOQE74QHT3ZRE3E4","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_8","alias_value":"BOQE74QH","created_at":"2026-05-18T12:32:16.446611+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/BOQE74QHT3ZRE3E4T2AMES3RL6","json":"https://pith.science/pith/BOQE74QHT3ZRE3E4T2AMES3RL6.json","graph_json":"https://pith.science/api/pith-number/BOQE74QHT3ZRE3E4T2AMES3RL6/graph.json","events_json":"https://pith.science/api/pith-number/BOQE74QHT3ZRE3E4T2AMES3RL6/events.json","paper":"https://pith.science/paper/BOQE74QH"},"agent_actions":{"view_html":"https://pith.science/pith/BOQE74QHT3ZRE3E4T2AMES3RL6","download_json":"https://pith.science/pith/BOQE74QHT3ZRE3E4T2AMES3RL6.json","view_paper":"https://pith.science/paper/BOQE74QH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.01552&json=true","fetch_graph":"https://pith.science/api/pith-number/BOQE74QHT3ZRE3E4T2AMES3RL6/graph.json","fetch_events":"https://pith.science/api/pith-number/BOQE74QHT3ZRE3E4T2AMES3RL6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BOQE74QHT3ZRE3E4T2AMES3RL6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BOQE74QHT3ZRE3E4T2AMES3RL6/action/storage_attestation","attest_author":"https://pith.science/pith/BOQE74QHT3ZRE3E4T2AMES3RL6/action/author_attestation","sign_citation":"https://pith.science/pith/BOQE74QHT3ZRE3E4T2AMES3RL6/action/citation_signature","submit_replication":"https://pith.science/pith/BOQE74QHT3ZRE3E4T2AMES3RL6/action/replication_record"}},"created_at":"2026-05-18T00:19:14.641507+00:00","updated_at":"2026-05-18T00:19:14.641507+00:00"}