{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:VSAL4ELOPU5NTQ64A4KKGVW6OA","short_pith_number":"pith:VSAL4ELO","schema_version":"1.0","canonical_sha256":"ac80be116e7d3ad9c3dc0714a356de703d3c047cc93c0ab6cdc31881af086053","source":{"kind":"arxiv","id":"1906.02940","version":3},"attestation_state":"computed","paper":{"title":"Selfie: Self-supervised Pretraining for Image Embedding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","eess.IV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Minh-Thang Luong, Quoc V. Le, Trieu H. Trinh","submitted_at":"2019-06-07T07:47:24Z","abstract_excerpt":"We introduce a pretraining technique called Selfie, which stands for SELFie supervised Image Embedding. Selfie generalizes the concept of masked language modeling of BERT (Devlin et al., 2019) to continuous data, such as images, by making use of the Contrastive Predictive Coding loss (Oord et al., 2018). Given masked-out patches in an input image, our method learns to select the correct patch, among other \"distractor\" patches sampled from the same image, to fill in the masked location. This classification objective sidesteps the need for predicting exact pixel values of the target patches. 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":"1906.02940","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-07T07:47:24Z","cross_cats_sorted":["cs.CV","eess.IV","stat.ML"],"title_canon_sha256":"71b2f753c2545976efafbc458b02bb598d26b0ef5609dbbef64c066e8c90c85a","abstract_canon_sha256":"6e7359c430620cd9ebc53c967a135842a04a489e39054588adf672aef4abd234"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:23.976234Z","signature_b64":"8kw/9XXKr2emvoOW3O4Rn4moN7Dg4WxhtEUP14qT/hLFeCKauYoT50cgGJ5hdTnmOkFdTR7bLHT9zcgDgUfHCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac80be116e7d3ad9c3dc0714a356de703d3c047cc93c0ab6cdc31881af086053","last_reissued_at":"2026-05-17T23:39:23.975572Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:23.975572Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Selfie: Self-supervised Pretraining for Image Embedding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","eess.IV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Minh-Thang Luong, Quoc V. Le, Trieu H. Trinh","submitted_at":"2019-06-07T07:47:24Z","abstract_excerpt":"We introduce a pretraining technique called Selfie, which stands for SELFie supervised Image Embedding. Selfie generalizes the concept of masked language modeling of BERT (Devlin et al., 2019) to continuous data, such as images, by making use of the Contrastive Predictive Coding loss (Oord et al., 2018). Given masked-out patches in an input image, our method learns to select the correct patch, among other \"distractor\" patches sampled from the same image, to fill in the masked location. This classification objective sidesteps the need for predicting exact pixel values of the target patches. The"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.02940","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":"1906.02940","created_at":"2026-05-17T23:39:23.975720+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.02940v3","created_at":"2026-05-17T23:39:23.975720+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.02940","created_at":"2026-05-17T23:39:23.975720+00:00"},{"alias_kind":"pith_short_12","alias_value":"VSAL4ELOPU5N","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"VSAL4ELOPU5NTQ64","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"VSAL4ELO","created_at":"2026-05-18T12:33:30.264802+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2106.08254","citing_title":"BEiT: BERT Pre-Training of Image Transformers","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VSAL4ELOPU5NTQ64A4KKGVW6OA","json":"https://pith.science/pith/VSAL4ELOPU5NTQ64A4KKGVW6OA.json","graph_json":"https://pith.science/api/pith-number/VSAL4ELOPU5NTQ64A4KKGVW6OA/graph.json","events_json":"https://pith.science/api/pith-number/VSAL4ELOPU5NTQ64A4KKGVW6OA/events.json","paper":"https://pith.science/paper/VSAL4ELO"},"agent_actions":{"view_html":"https://pith.science/pith/VSAL4ELOPU5NTQ64A4KKGVW6OA","download_json":"https://pith.science/pith/VSAL4ELOPU5NTQ64A4KKGVW6OA.json","view_paper":"https://pith.science/paper/VSAL4ELO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.02940&json=true","fetch_graph":"https://pith.science/api/pith-number/VSAL4ELOPU5NTQ64A4KKGVW6OA/graph.json","fetch_events":"https://pith.science/api/pith-number/VSAL4ELOPU5NTQ64A4KKGVW6OA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VSAL4ELOPU5NTQ64A4KKGVW6OA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VSAL4ELOPU5NTQ64A4KKGVW6OA/action/storage_attestation","attest_author":"https://pith.science/pith/VSAL4ELOPU5NTQ64A4KKGVW6OA/action/author_attestation","sign_citation":"https://pith.science/pith/VSAL4ELOPU5NTQ64A4KKGVW6OA/action/citation_signature","submit_replication":"https://pith.science/pith/VSAL4ELOPU5NTQ64A4KKGVW6OA/action/replication_record"}},"created_at":"2026-05-17T23:39:23.975720+00:00","updated_at":"2026-05-17T23:39:23.975720+00:00"}