{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:6I2XKELJ3LR3QSYUCO6RNSOSJ4","short_pith_number":"pith:6I2XKELJ","schema_version":"1.0","canonical_sha256":"f235751169dae3b84b1413bd16c9d24f36265205bc55bd5b1dfa29a6ea6a794d","source":{"kind":"arxiv","id":"1903.03161","version":1},"attestation_state":"computed","paper":{"title":"Deep CNN-based Multi-task Learning for Open-Set Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Poojan Oza, Vishal M. Patel","submitted_at":"2019-03-07T20:11:32Z","abstract_excerpt":"We propose a novel deep convolutional neural network (CNN) based multi-task learning approach for open-set visual recognition. We combine a classifier network and a decoder network with a shared feature extractor network within a multi-task learning framework. We show that this approach results in better open-set recognition accuracy. In our approach, reconstruction errors from the decoder network are utilized for open-set rejection. In addition, we model the tail of the reconstruction error distribution from the known classes using the statistical Extreme Value Theory to improve the overall p"},"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":"1903.03161","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-07T20:11:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0381c9167cc4a7cc38e25d060b75b97ce64c1f59a4d420542b83dd6181f9310c","abstract_canon_sha256":"b1f5a110bfc36cab2478c81aef75ffb9a3bd05ee3646b54417da6717ab8333f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:46.283235Z","signature_b64":"UtnptYFjZnx1FEeQ4h4ypCjka625H5oxHu4v1YoFqitcxPaxgfXeL7VcAmMUjYtj+Lf703aVWzxkalyDVuXqCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f235751169dae3b84b1413bd16c9d24f36265205bc55bd5b1dfa29a6ea6a794d","last_reissued_at":"2026-05-17T23:51:46.282723Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:46.282723Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep CNN-based Multi-task Learning for Open-Set Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Poojan Oza, Vishal M. Patel","submitted_at":"2019-03-07T20:11:32Z","abstract_excerpt":"We propose a novel deep convolutional neural network (CNN) based multi-task learning approach for open-set visual recognition. We combine a classifier network and a decoder network with a shared feature extractor network within a multi-task learning framework. We show that this approach results in better open-set recognition accuracy. In our approach, reconstruction errors from the decoder network are utilized for open-set rejection. In addition, we model the tail of the reconstruction error distribution from the known classes using the statistical Extreme Value Theory to improve the overall p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.03161","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":"1903.03161","created_at":"2026-05-17T23:51:46.282815+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.03161v1","created_at":"2026-05-17T23:51:46.282815+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.03161","created_at":"2026-05-17T23:51:46.282815+00:00"},{"alias_kind":"pith_short_12","alias_value":"6I2XKELJ3LR3","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"6I2XKELJ3LR3QSYU","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"6I2XKELJ","created_at":"2026-05-18T12:33:10.108867+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/6I2XKELJ3LR3QSYUCO6RNSOSJ4","json":"https://pith.science/pith/6I2XKELJ3LR3QSYUCO6RNSOSJ4.json","graph_json":"https://pith.science/api/pith-number/6I2XKELJ3LR3QSYUCO6RNSOSJ4/graph.json","events_json":"https://pith.science/api/pith-number/6I2XKELJ3LR3QSYUCO6RNSOSJ4/events.json","paper":"https://pith.science/paper/6I2XKELJ"},"agent_actions":{"view_html":"https://pith.science/pith/6I2XKELJ3LR3QSYUCO6RNSOSJ4","download_json":"https://pith.science/pith/6I2XKELJ3LR3QSYUCO6RNSOSJ4.json","view_paper":"https://pith.science/paper/6I2XKELJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.03161&json=true","fetch_graph":"https://pith.science/api/pith-number/6I2XKELJ3LR3QSYUCO6RNSOSJ4/graph.json","fetch_events":"https://pith.science/api/pith-number/6I2XKELJ3LR3QSYUCO6RNSOSJ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6I2XKELJ3LR3QSYUCO6RNSOSJ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6I2XKELJ3LR3QSYUCO6RNSOSJ4/action/storage_attestation","attest_author":"https://pith.science/pith/6I2XKELJ3LR3QSYUCO6RNSOSJ4/action/author_attestation","sign_citation":"https://pith.science/pith/6I2XKELJ3LR3QSYUCO6RNSOSJ4/action/citation_signature","submit_replication":"https://pith.science/pith/6I2XKELJ3LR3QSYUCO6RNSOSJ4/action/replication_record"}},"created_at":"2026-05-17T23:51:46.282815+00:00","updated_at":"2026-05-17T23:51:46.282815+00:00"}