{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:WJTBYF6FZ4WNLSRBJKPHKCAQ6I","short_pith_number":"pith:WJTBYF6F","schema_version":"1.0","canonical_sha256":"b2661c17c5cf2cd5ca214a9e750810f21123f0d716ecbcbb13e6d65173d84001","source":{"kind":"arxiv","id":"2101.08533","version":5},"attestation_state":"computed","paper":{"title":"Eliminate Deviation with Deviation for Data Augmentation and a General Multi-modal Data Learning Method","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lifei Chen, Liqing Huang, Yunpeng Gong","submitted_at":"2021-01-21T10:33:02Z","abstract_excerpt":"One of the challenges of computer vision is that it needs to adapt to color deviations in changeable environments. Therefore, minimizing the adverse effects of color deviation on the prediction is one of the main goals of vision task. Current solutions focus on using generative models to augment training data to enhance the invariance of input variation. However, such methods often introduce new noise, which limits the gain from generated data. To this end, this paper proposes a strategy eliminate deviation with deviation, which is named Random Color Dropout (RCD). Our hypothesis is that if th"},"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":"2101.08533","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-01-21T10:33:02Z","cross_cats_sorted":[],"title_canon_sha256":"becde84ad844a728aef3a3c48498e07733c2ac6150fe42eaf83de6830963df39","abstract_canon_sha256":"90d6734c7b74175001568cce373169d1a5c4d675ac1dc5ce24e2257eb8a78ba9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:31:10.376441Z","signature_b64":"cn++oKpre7vW9mWyLwf63XU8yT7YpnzEjKc5RgQnnp4GxFDXRcEMwbm3PqaOuLLnbmRkSnOvniZ0WFwRfi0NCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2661c17c5cf2cd5ca214a9e750810f21123f0d716ecbcbb13e6d65173d84001","last_reissued_at":"2026-07-05T04:31:10.375995Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:31:10.375995Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Eliminate Deviation with Deviation for Data Augmentation and a General Multi-modal Data Learning Method","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lifei Chen, Liqing Huang, Yunpeng Gong","submitted_at":"2021-01-21T10:33:02Z","abstract_excerpt":"One of the challenges of computer vision is that it needs to adapt to color deviations in changeable environments. Therefore, minimizing the adverse effects of color deviation on the prediction is one of the main goals of vision task. Current solutions focus on using generative models to augment training data to enhance the invariance of input variation. However, such methods often introduce new noise, which limits the gain from generated data. To this end, this paper proposes a strategy eliminate deviation with deviation, which is named Random Color Dropout (RCD). Our hypothesis is that if th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.08533","kind":"arxiv","version":5},"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/2101.08533/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":"2101.08533","created_at":"2026-07-05T04:31:10.376052+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.08533v5","created_at":"2026-07-05T04:31:10.376052+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.08533","created_at":"2026-07-05T04:31:10.376052+00:00"},{"alias_kind":"pith_short_12","alias_value":"WJTBYF6FZ4WN","created_at":"2026-07-05T04:31:10.376052+00:00"},{"alias_kind":"pith_short_16","alias_value":"WJTBYF6FZ4WNLSRB","created_at":"2026-07-05T04:31:10.376052+00:00"},{"alias_kind":"pith_short_8","alias_value":"WJTBYF6F","created_at":"2026-07-05T04:31:10.376052+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2406.16042","citing_title":"Pose-dIVE: Pose-Diversified Augmentation with Diffusion Model for Person Re-Identification","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WJTBYF6FZ4WNLSRBJKPHKCAQ6I","json":"https://pith.science/pith/WJTBYF6FZ4WNLSRBJKPHKCAQ6I.json","graph_json":"https://pith.science/api/pith-number/WJTBYF6FZ4WNLSRBJKPHKCAQ6I/graph.json","events_json":"https://pith.science/api/pith-number/WJTBYF6FZ4WNLSRBJKPHKCAQ6I/events.json","paper":"https://pith.science/paper/WJTBYF6F"},"agent_actions":{"view_html":"https://pith.science/pith/WJTBYF6FZ4WNLSRBJKPHKCAQ6I","download_json":"https://pith.science/pith/WJTBYF6FZ4WNLSRBJKPHKCAQ6I.json","view_paper":"https://pith.science/paper/WJTBYF6F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.08533&json=true","fetch_graph":"https://pith.science/api/pith-number/WJTBYF6FZ4WNLSRBJKPHKCAQ6I/graph.json","fetch_events":"https://pith.science/api/pith-number/WJTBYF6FZ4WNLSRBJKPHKCAQ6I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WJTBYF6FZ4WNLSRBJKPHKCAQ6I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WJTBYF6FZ4WNLSRBJKPHKCAQ6I/action/storage_attestation","attest_author":"https://pith.science/pith/WJTBYF6FZ4WNLSRBJKPHKCAQ6I/action/author_attestation","sign_citation":"https://pith.science/pith/WJTBYF6FZ4WNLSRBJKPHKCAQ6I/action/citation_signature","submit_replication":"https://pith.science/pith/WJTBYF6FZ4WNLSRBJKPHKCAQ6I/action/replication_record"}},"created_at":"2026-07-05T04:31:10.376052+00:00","updated_at":"2026-07-05T04:31:10.376052+00:00"}