{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LQVZUMNPX5C52JFIZHIZZB23KJ","short_pith_number":"pith:LQVZUMNP","schema_version":"1.0","canonical_sha256":"5c2b9a31afbf45dd24a8c9d19c875b524ae34238747405d5d80d37e73559aad9","source":{"kind":"arxiv","id":"2305.08661","version":1},"attestation_state":"computed","paper":{"title":"Global and Local Mixture Consistency Cumulative Learning for Long-tailed Visual Recognitions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Fei Du, Fengtao Nan, Peng Yang, Qi Jia, Xiaoting Chen, Yun Yang","submitted_at":"2023-05-15T14:09:09Z","abstract_excerpt":"In this paper, our goal is to design a simple learning paradigm for long-tail visual recognition, which not only improves the robustness of the feature extractor but also alleviates the bias of the classifier towards head classes while reducing the training skills and overhead. We propose an efficient one-stage training strategy for long-tailed visual recognition called Global and Local Mixture Consistency cumulative learning (GLMC). Our core ideas are twofold: (1) a global and local mixture consistency loss improves the robustness of the feature extractor. Specifically, we generate two augmen"},"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":"2305.08661","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-15T14:09:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2b4ed86301eae600068c87a9fb0f9eefe4c7db451c2537c2ea7ef4a34af9ffdb","abstract_canon_sha256":"b49481f97bc07a4c2cace5b43baad7d69fe9138d588b27b7976acb52958f1b27"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:10:04.610062Z","signature_b64":"NE5XK7x0OWk8VcgUvVyb4fE/dUjF2tsZzjyoWs2mkp0EVd/QzcIocQvhpJEZnE9nFSKoiIza7VpMynNtjd4NCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c2b9a31afbf45dd24a8c9d19c875b524ae34238747405d5d80d37e73559aad9","last_reissued_at":"2026-07-05T06:10:04.609662Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:10:04.609662Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Global and Local Mixture Consistency Cumulative Learning for Long-tailed Visual Recognitions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Fei Du, Fengtao Nan, Peng Yang, Qi Jia, Xiaoting Chen, Yun Yang","submitted_at":"2023-05-15T14:09:09Z","abstract_excerpt":"In this paper, our goal is to design a simple learning paradigm for long-tail visual recognition, which not only improves the robustness of the feature extractor but also alleviates the bias of the classifier towards head classes while reducing the training skills and overhead. We propose an efficient one-stage training strategy for long-tailed visual recognition called Global and Local Mixture Consistency cumulative learning (GLMC). Our core ideas are twofold: (1) a global and local mixture consistency loss improves the robustness of the feature extractor. Specifically, we generate two augmen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.08661","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/2305.08661/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":"2305.08661","created_at":"2026-07-05T06:10:04.609721+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.08661v1","created_at":"2026-07-05T06:10:04.609721+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.08661","created_at":"2026-07-05T06:10:04.609721+00:00"},{"alias_kind":"pith_short_12","alias_value":"LQVZUMNPX5C5","created_at":"2026-07-05T06:10:04.609721+00:00"},{"alias_kind":"pith_short_16","alias_value":"LQVZUMNPX5C52JFI","created_at":"2026-07-05T06:10:04.609721+00:00"},{"alias_kind":"pith_short_8","alias_value":"LQVZUMNP","created_at":"2026-07-05T06:10:04.609721+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/LQVZUMNPX5C52JFIZHIZZB23KJ","json":"https://pith.science/pith/LQVZUMNPX5C52JFIZHIZZB23KJ.json","graph_json":"https://pith.science/api/pith-number/LQVZUMNPX5C52JFIZHIZZB23KJ/graph.json","events_json":"https://pith.science/api/pith-number/LQVZUMNPX5C52JFIZHIZZB23KJ/events.json","paper":"https://pith.science/paper/LQVZUMNP"},"agent_actions":{"view_html":"https://pith.science/pith/LQVZUMNPX5C52JFIZHIZZB23KJ","download_json":"https://pith.science/pith/LQVZUMNPX5C52JFIZHIZZB23KJ.json","view_paper":"https://pith.science/paper/LQVZUMNP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.08661&json=true","fetch_graph":"https://pith.science/api/pith-number/LQVZUMNPX5C52JFIZHIZZB23KJ/graph.json","fetch_events":"https://pith.science/api/pith-number/LQVZUMNPX5C52JFIZHIZZB23KJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LQVZUMNPX5C52JFIZHIZZB23KJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LQVZUMNPX5C52JFIZHIZZB23KJ/action/storage_attestation","attest_author":"https://pith.science/pith/LQVZUMNPX5C52JFIZHIZZB23KJ/action/author_attestation","sign_citation":"https://pith.science/pith/LQVZUMNPX5C52JFIZHIZZB23KJ/action/citation_signature","submit_replication":"https://pith.science/pith/LQVZUMNPX5C52JFIZHIZZB23KJ/action/replication_record"}},"created_at":"2026-07-05T06:10:04.609721+00:00","updated_at":"2026-07-05T06:10:04.609721+00:00"}