{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:WBIZBT5TTOSCC6RD25NWLGIWR6","short_pith_number":"pith:WBIZBT5T","schema_version":"1.0","canonical_sha256":"b05190cfb39ba4217a23d75b6599168f93c6ba85e25ff5fff4aac94b8aa911d2","source":{"kind":"arxiv","id":"1903.02196","version":1},"attestation_state":"computed","paper":{"title":"Deep Transfer Learning for Multiple Class Novelty Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Pramuditha Perera, Vishal M. Patel","submitted_at":"2019-03-06T06:36:57Z","abstract_excerpt":"We propose a transfer learning-based solution for the problem of multiple class novelty detection. In particular, we propose an end-to-end deep-learning based approach in which we investigate how the knowledge contained in an external, out-of-distributional dataset can be used to improve the performance of a deep network for visual novelty detection. Our solution differs from the standard deep classification networks on two accounts. First, we use a novel loss function, membership loss, in addition to the classical cross-entropy loss for training networks. Secondly, we use the knowledge from t"},"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":"1903.02196","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-06T06:36:57Z","cross_cats_sorted":[],"title_canon_sha256":"85774818b0f0e900e18a8aa544ea63fa6fc9f372795c05ed0685d1d13be40b94","abstract_canon_sha256":"8b5f0d6c99dd6d9f1dc9a6c55d3ccfe8c09bc6dcd485c2f43e3c8c7bb4d95ed8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:56.506814Z","signature_b64":"tyZSqASvn+aqr4IgdNb3OVC4iAevLSCFdJjojZK876bgQUzJb0EQTr9TwBZFj8gzMX8O+XLZg07nlWooK8IYCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b05190cfb39ba4217a23d75b6599168f93c6ba85e25ff5fff4aac94b8aa911d2","last_reissued_at":"2026-05-17T23:51:56.506344Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:56.506344Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Transfer Learning for Multiple Class Novelty Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Pramuditha Perera, Vishal M. Patel","submitted_at":"2019-03-06T06:36:57Z","abstract_excerpt":"We propose a transfer learning-based solution for the problem of multiple class novelty detection. In particular, we propose an end-to-end deep-learning based approach in which we investigate how the knowledge contained in an external, out-of-distributional dataset can be used to improve the performance of a deep network for visual novelty detection. Our solution differs from the standard deep classification networks on two accounts. First, we use a novel loss function, membership loss, in addition to the classical cross-entropy loss for training networks. Secondly, we use the knowledge from t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.02196","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":"1903.02196","created_at":"2026-05-17T23:51:56.506409+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.02196v1","created_at":"2026-05-17T23:51:56.506409+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.02196","created_at":"2026-05-17T23:51:56.506409+00:00"},{"alias_kind":"pith_short_12","alias_value":"WBIZBT5TTOSC","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"WBIZBT5TTOSCC6RD","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"WBIZBT5T","created_at":"2026-05-18T12:33:30.264802+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/WBIZBT5TTOSCC6RD25NWLGIWR6","json":"https://pith.science/pith/WBIZBT5TTOSCC6RD25NWLGIWR6.json","graph_json":"https://pith.science/api/pith-number/WBIZBT5TTOSCC6RD25NWLGIWR6/graph.json","events_json":"https://pith.science/api/pith-number/WBIZBT5TTOSCC6RD25NWLGIWR6/events.json","paper":"https://pith.science/paper/WBIZBT5T"},"agent_actions":{"view_html":"https://pith.science/pith/WBIZBT5TTOSCC6RD25NWLGIWR6","download_json":"https://pith.science/pith/WBIZBT5TTOSCC6RD25NWLGIWR6.json","view_paper":"https://pith.science/paper/WBIZBT5T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.02196&json=true","fetch_graph":"https://pith.science/api/pith-number/WBIZBT5TTOSCC6RD25NWLGIWR6/graph.json","fetch_events":"https://pith.science/api/pith-number/WBIZBT5TTOSCC6RD25NWLGIWR6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WBIZBT5TTOSCC6RD25NWLGIWR6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WBIZBT5TTOSCC6RD25NWLGIWR6/action/storage_attestation","attest_author":"https://pith.science/pith/WBIZBT5TTOSCC6RD25NWLGIWR6/action/author_attestation","sign_citation":"https://pith.science/pith/WBIZBT5TTOSCC6RD25NWLGIWR6/action/citation_signature","submit_replication":"https://pith.science/pith/WBIZBT5TTOSCC6RD25NWLGIWR6/action/replication_record"}},"created_at":"2026-05-17T23:51:56.506409+00:00","updated_at":"2026-05-17T23:51:56.506409+00:00"}