{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:MGB34NQCV5DEITOJFR5CB4CSCH","short_pith_number":"pith:MGB34NQC","schema_version":"1.0","canonical_sha256":"6183be3602af46444dc92c7a20f05211de990a48c18947ccaebcd2324e3c853e","source":{"kind":"arxiv","id":"2106.15252","version":1},"attestation_state":"computed","paper":{"title":"AutoNovel: Automatically Discovering and Learning Novel Visual Categories","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea Vedaldi, Andrew Zisserman, Kai Han, S\\'ebastien Ehrhardt, Sylvestre-Alvise Rebuffi","submitted_at":"2021-06-29T11:12:16Z","abstract_excerpt":"We tackle the problem of discovering novel classes in an image collection given labelled examples of other classes. We present a new approach called AutoNovel to address this problem by combining three ideas: (1) we suggest that the common approach of bootstrapping an image representation using the labelled data only introduces an unwanted bias, and that this can be avoided by using self-supervised learning to train the representation from scratch on the union of labelled and unlabelled data; (2) we use ranking statistics to transfer the model's knowledge of the labelled classes to the problem"},"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":"2106.15252","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-29T11:12:16Z","cross_cats_sorted":[],"title_canon_sha256":"eb6451059cd557f93ffe6b70ffcf4453da3c0843d6a2aff40a4d06358d70836f","abstract_canon_sha256":"90bcfd559c14612f61aef6f28fc31a4b3b227f461687861171151856e263e241"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:53:15.261629Z","signature_b64":"022fELkqLY8dOnxJ0QUjly9v2KreEZ16AbTfyPko99oBmArGOreN3nud0vXAwy0WTUUFoEG/+fE0vqE0XOkqBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6183be3602af46444dc92c7a20f05211de990a48c18947ccaebcd2324e3c853e","last_reissued_at":"2026-07-05T02:53:15.261216Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:53:15.261216Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AutoNovel: Automatically Discovering and Learning Novel Visual Categories","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea Vedaldi, Andrew Zisserman, Kai Han, S\\'ebastien Ehrhardt, Sylvestre-Alvise Rebuffi","submitted_at":"2021-06-29T11:12:16Z","abstract_excerpt":"We tackle the problem of discovering novel classes in an image collection given labelled examples of other classes. We present a new approach called AutoNovel to address this problem by combining three ideas: (1) we suggest that the common approach of bootstrapping an image representation using the labelled data only introduces an unwanted bias, and that this can be avoided by using self-supervised learning to train the representation from scratch on the union of labelled and unlabelled data; (2) we use ranking statistics to transfer the model's knowledge of the labelled classes to the problem"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.15252","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/2106.15252/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":"2106.15252","created_at":"2026-07-05T02:53:15.261273+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.15252v1","created_at":"2026-07-05T02:53:15.261273+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.15252","created_at":"2026-07-05T02:53:15.261273+00:00"},{"alias_kind":"pith_short_12","alias_value":"MGB34NQCV5DE","created_at":"2026-07-05T02:53:15.261273+00:00"},{"alias_kind":"pith_short_16","alias_value":"MGB34NQCV5DEITOJ","created_at":"2026-07-05T02:53:15.261273+00:00"},{"alias_kind":"pith_short_8","alias_value":"MGB34NQC","created_at":"2026-07-05T02:53:15.261273+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/MGB34NQCV5DEITOJFR5CB4CSCH","json":"https://pith.science/pith/MGB34NQCV5DEITOJFR5CB4CSCH.json","graph_json":"https://pith.science/api/pith-number/MGB34NQCV5DEITOJFR5CB4CSCH/graph.json","events_json":"https://pith.science/api/pith-number/MGB34NQCV5DEITOJFR5CB4CSCH/events.json","paper":"https://pith.science/paper/MGB34NQC"},"agent_actions":{"view_html":"https://pith.science/pith/MGB34NQCV5DEITOJFR5CB4CSCH","download_json":"https://pith.science/pith/MGB34NQCV5DEITOJFR5CB4CSCH.json","view_paper":"https://pith.science/paper/MGB34NQC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.15252&json=true","fetch_graph":"https://pith.science/api/pith-number/MGB34NQCV5DEITOJFR5CB4CSCH/graph.json","fetch_events":"https://pith.science/api/pith-number/MGB34NQCV5DEITOJFR5CB4CSCH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MGB34NQCV5DEITOJFR5CB4CSCH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MGB34NQCV5DEITOJFR5CB4CSCH/action/storage_attestation","attest_author":"https://pith.science/pith/MGB34NQCV5DEITOJFR5CB4CSCH/action/author_attestation","sign_citation":"https://pith.science/pith/MGB34NQCV5DEITOJFR5CB4CSCH/action/citation_signature","submit_replication":"https://pith.science/pith/MGB34NQCV5DEITOJFR5CB4CSCH/action/replication_record"}},"created_at":"2026-07-05T02:53:15.261273+00:00","updated_at":"2026-07-05T02:53:15.261273+00:00"}