{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:T5U4PKZF67ZDGTHSLUBEADGXCG","short_pith_number":"pith:T5U4PKZF","schema_version":"1.0","canonical_sha256":"9f69c7ab25f7f2334cf25d02400cd71197a68601b216808a4762e937fce49a60","source":{"kind":"arxiv","id":"2012.14629","version":1},"attestation_state":"computed","paper":{"title":"TrustMAE: A Noise-Resilient Defect Classification Framework using Memory-Augmented Auto-Encoders with Trust Regions","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daniel Stanley Tan, Trista Pei-Chun Chen, Wei-Chao Chen, Yi-Chun Chen","submitted_at":"2020-12-29T06:57:36Z","abstract_excerpt":"In this paper, we propose a framework called TrustMAE to address the problem of product defect classification. Instead of relying on defective images that are difficult to collect and laborious to label, our framework can accept datasets with unlabeled images. Moreover, unlike most anomaly detection methods, our approach is robust against noises, or defective images, in the training dataset. Our framework uses a memory-augmented auto-encoder with a sparse memory addressing scheme to avoid over-generalizing the auto-encoder, and a novel trust-region memory updating scheme to keep the noises awa"},"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":"2012.14629","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2020-12-29T06:57:36Z","cross_cats_sorted":[],"title_canon_sha256":"b26984762f4e55755b35453a2f1cbb2e6200a9809e512efc08fbf1dba0b244f2","abstract_canon_sha256":"72d444dbf3da6721e5cc4204c4e9a6af18d07c4da49f7a20da3d1874e89a1c45"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:03:00.015435Z","signature_b64":"6N8Fh9xa9LkowsX+j54hL0n1LrrvZqvCz9YPnyElC9JGe54LG7SybtTbVEW8ijlUrmveNaFEE/1EHDgKM2u+DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f69c7ab25f7f2334cf25d02400cd71197a68601b216808a4762e937fce49a60","last_reissued_at":"2026-07-05T02:03:00.015064Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:03:00.015064Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TrustMAE: A Noise-Resilient Defect Classification Framework using Memory-Augmented Auto-Encoders with Trust Regions","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daniel Stanley Tan, Trista Pei-Chun Chen, Wei-Chao Chen, Yi-Chun Chen","submitted_at":"2020-12-29T06:57:36Z","abstract_excerpt":"In this paper, we propose a framework called TrustMAE to address the problem of product defect classification. Instead of relying on defective images that are difficult to collect and laborious to label, our framework can accept datasets with unlabeled images. Moreover, unlike most anomaly detection methods, our approach is robust against noises, or defective images, in the training dataset. Our framework uses a memory-augmented auto-encoder with a sparse memory addressing scheme to avoid over-generalizing the auto-encoder, and a novel trust-region memory updating scheme to keep the noises awa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.14629","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/2012.14629/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":"2012.14629","created_at":"2026-07-05T02:03:00.015126+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.14629v1","created_at":"2026-07-05T02:03:00.015126+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.14629","created_at":"2026-07-05T02:03:00.015126+00:00"},{"alias_kind":"pith_short_12","alias_value":"T5U4PKZF67ZD","created_at":"2026-07-05T02:03:00.015126+00:00"},{"alias_kind":"pith_short_16","alias_value":"T5U4PKZF67ZDGTHS","created_at":"2026-07-05T02:03:00.015126+00:00"},{"alias_kind":"pith_short_8","alias_value":"T5U4PKZF","created_at":"2026-07-05T02:03:00.015126+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/T5U4PKZF67ZDGTHSLUBEADGXCG","json":"https://pith.science/pith/T5U4PKZF67ZDGTHSLUBEADGXCG.json","graph_json":"https://pith.science/api/pith-number/T5U4PKZF67ZDGTHSLUBEADGXCG/graph.json","events_json":"https://pith.science/api/pith-number/T5U4PKZF67ZDGTHSLUBEADGXCG/events.json","paper":"https://pith.science/paper/T5U4PKZF"},"agent_actions":{"view_html":"https://pith.science/pith/T5U4PKZF67ZDGTHSLUBEADGXCG","download_json":"https://pith.science/pith/T5U4PKZF67ZDGTHSLUBEADGXCG.json","view_paper":"https://pith.science/paper/T5U4PKZF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.14629&json=true","fetch_graph":"https://pith.science/api/pith-number/T5U4PKZF67ZDGTHSLUBEADGXCG/graph.json","fetch_events":"https://pith.science/api/pith-number/T5U4PKZF67ZDGTHSLUBEADGXCG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T5U4PKZF67ZDGTHSLUBEADGXCG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T5U4PKZF67ZDGTHSLUBEADGXCG/action/storage_attestation","attest_author":"https://pith.science/pith/T5U4PKZF67ZDGTHSLUBEADGXCG/action/author_attestation","sign_citation":"https://pith.science/pith/T5U4PKZF67ZDGTHSLUBEADGXCG/action/citation_signature","submit_replication":"https://pith.science/pith/T5U4PKZF67ZDGTHSLUBEADGXCG/action/replication_record"}},"created_at":"2026-07-05T02:03:00.015126+00:00","updated_at":"2026-07-05T02:03:00.015126+00:00"}