{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:MF2VAJV5GUCMVYENE4EMFYW4W6","short_pith_number":"pith:MF2VAJV5","schema_version":"1.0","canonical_sha256":"61755026bd3504cae08d2708c2e2dcb78d983a7bd647740450b657e414c45354","source":{"kind":"arxiv","id":"1904.07595","version":2},"attestation_state":"computed","paper":{"title":"Detecting the Unexpected via Image Resynthesis","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Krishna Nakka, Krzysztof Lis, Mathieu Salzmann, Pascal Fua","submitted_at":"2019-04-16T11:08:39Z","abstract_excerpt":"Classical semantic segmentation methods, including the recent deep learning ones, assume that all classes observed at test time have been seen during training. In this paper, we tackle the more realistic scenario where unexpected objects of unknown classes can appear at test time. The main trends in this area either leverage the notion of prediction uncertainty to flag the regions with low confidence as unknown, or rely on autoencoders and highlight poorly-decoded regions. Having observed that, in both cases, the detected regions typically do not correspond to unexpected objects, in this paper"},"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":"1904.07595","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2019-04-16T11:08:39Z","cross_cats_sorted":[],"title_canon_sha256":"acb350711eef982f6d82ee73bdad1da5b7b11654ef3a2a244b160631a22615df","abstract_canon_sha256":"638bef686d4c395ae23262e9d0c9bdb3c3b007b740065b7c3e91e8b189811c21"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:19.546873Z","signature_b64":"wPe+8prq4hsQsaugGyNztpCLX+VBUx0m0Cy534LZk2eQnmaakGmQUduvx4go6cB+DagVjeN6JzXNhmpvefLMDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61755026bd3504cae08d2708c2e2dcb78d983a7bd647740450b657e414c45354","last_reissued_at":"2026-05-17T23:48:19.546194Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:19.546194Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Detecting the Unexpected via Image Resynthesis","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Krishna Nakka, Krzysztof Lis, Mathieu Salzmann, Pascal Fua","submitted_at":"2019-04-16T11:08:39Z","abstract_excerpt":"Classical semantic segmentation methods, including the recent deep learning ones, assume that all classes observed at test time have been seen during training. In this paper, we tackle the more realistic scenario where unexpected objects of unknown classes can appear at test time. The main trends in this area either leverage the notion of prediction uncertainty to flag the regions with low confidence as unknown, or rely on autoencoders and highlight poorly-decoded regions. Having observed that, in both cases, the detected regions typically do not correspond to unexpected objects, in this paper"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.07595","kind":"arxiv","version":2},"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":"1904.07595","created_at":"2026-05-17T23:48:19.546302+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.07595v2","created_at":"2026-05-17T23:48:19.546302+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.07595","created_at":"2026-05-17T23:48:19.546302+00:00"},{"alias_kind":"pith_short_12","alias_value":"MF2VAJV5GUCM","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_16","alias_value":"MF2VAJV5GUCMVYEN","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_8","alias_value":"MF2VAJV5","created_at":"2026-05-18T12:33:21.387695+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.10765","citing_title":"Neural Network Meta Classifier: Improving the Reliability of Anomaly Segmentation","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MF2VAJV5GUCMVYENE4EMFYW4W6","json":"https://pith.science/pith/MF2VAJV5GUCMVYENE4EMFYW4W6.json","graph_json":"https://pith.science/api/pith-number/MF2VAJV5GUCMVYENE4EMFYW4W6/graph.json","events_json":"https://pith.science/api/pith-number/MF2VAJV5GUCMVYENE4EMFYW4W6/events.json","paper":"https://pith.science/paper/MF2VAJV5"},"agent_actions":{"view_html":"https://pith.science/pith/MF2VAJV5GUCMVYENE4EMFYW4W6","download_json":"https://pith.science/pith/MF2VAJV5GUCMVYENE4EMFYW4W6.json","view_paper":"https://pith.science/paper/MF2VAJV5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.07595&json=true","fetch_graph":"https://pith.science/api/pith-number/MF2VAJV5GUCMVYENE4EMFYW4W6/graph.json","fetch_events":"https://pith.science/api/pith-number/MF2VAJV5GUCMVYENE4EMFYW4W6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MF2VAJV5GUCMVYENE4EMFYW4W6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MF2VAJV5GUCMVYENE4EMFYW4W6/action/storage_attestation","attest_author":"https://pith.science/pith/MF2VAJV5GUCMVYENE4EMFYW4W6/action/author_attestation","sign_citation":"https://pith.science/pith/MF2VAJV5GUCMVYENE4EMFYW4W6/action/citation_signature","submit_replication":"https://pith.science/pith/MF2VAJV5GUCMVYENE4EMFYW4W6/action/replication_record"}},"created_at":"2026-05-17T23:48:19.546302+00:00","updated_at":"2026-05-17T23:48:19.546302+00:00"}