{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:HYUO4AKPOS24E7J64TVFRMPFJX","short_pith_number":"pith:HYUO4AKP","schema_version":"1.0","canonical_sha256":"3e28ee014f74b5c27d3ee4ea58b1e54dee41e0ff5f472bc9a51be2e533b5003d","source":{"kind":"arxiv","id":"1901.09891","version":2},"attestation_state":"computed","paper":{"title":"See Better Before Looking Closer: Weakly Supervised Data Augmentation Network for Fine-Grained Visual Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Honggang Qi, Qingming Huang, Tao Hu, Yan Lu","submitted_at":"2019-01-26T02:03:27Z","abstract_excerpt":"Data augmentation is usually adopted to increase the amount of training data, prevent overfitting and improve the performance of deep models. However, in practice, random data augmentation, such as random image cropping, is low-efficiency and might introduce many uncontrolled background noises. In this paper, we propose Weakly Supervised Data Augmentation Network (WS-DAN) to explore the potential of data augmentation. Specifically, for each training image, we first generate attention maps to represent the object's discriminative parts by weakly supervised learning. Next, we augment the image g"},"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":"1901.09891","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-01-26T02:03:27Z","cross_cats_sorted":[],"title_canon_sha256":"7996ca29c03a21da362d181f231fc907987fb378514a18eeb3c16dbea399636f","abstract_canon_sha256":"44e26164a8e7a3cd257c80ce3e0a3cdaf13524ff0499803055efdb00ff98d29e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:50:36.091386Z","signature_b64":"HqoT58ozFJ+wJsTx32uVP7uxMRga38MZre6uV8koYaDrN617KZtkSWTOz1Sau7/AGKTPLZZVHsQP1HUXc68fDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e28ee014f74b5c27d3ee4ea58b1e54dee41e0ff5f472bc9a51be2e533b5003d","last_reissued_at":"2026-05-17T23:50:36.090891Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:50:36.090891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"See Better Before Looking Closer: Weakly Supervised Data Augmentation Network for Fine-Grained Visual Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Honggang Qi, Qingming Huang, Tao Hu, Yan Lu","submitted_at":"2019-01-26T02:03:27Z","abstract_excerpt":"Data augmentation is usually adopted to increase the amount of training data, prevent overfitting and improve the performance of deep models. However, in practice, random data augmentation, such as random image cropping, is low-efficiency and might introduce many uncontrolled background noises. In this paper, we propose Weakly Supervised Data Augmentation Network (WS-DAN) to explore the potential of data augmentation. Specifically, for each training image, we first generate attention maps to represent the object's discriminative parts by weakly supervised learning. Next, we augment the image g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.09891","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":"1901.09891","created_at":"2026-05-17T23:50:36.090961+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.09891v2","created_at":"2026-05-17T23:50:36.090961+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.09891","created_at":"2026-05-17T23:50:36.090961+00:00"},{"alias_kind":"pith_short_12","alias_value":"HYUO4AKPOS24","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_16","alias_value":"HYUO4AKPOS24E7J6","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_8","alias_value":"HYUO4AKP","created_at":"2026-05-18T12:33:18.533446+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.15689","citing_title":"How to Choose Your Teacher for Fine Grained Image Recognition","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18700","citing_title":"A Large-Scale Study on the Accuracy vs Cost Trade-offs of Training and Evaluation Settings in Fine-Grained Image Recognition","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2006.07397","citing_title":"The DeepFake Detection Challenge (DFDC) Dataset","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HYUO4AKPOS24E7J64TVFRMPFJX","json":"https://pith.science/pith/HYUO4AKPOS24E7J64TVFRMPFJX.json","graph_json":"https://pith.science/api/pith-number/HYUO4AKPOS24E7J64TVFRMPFJX/graph.json","events_json":"https://pith.science/api/pith-number/HYUO4AKPOS24E7J64TVFRMPFJX/events.json","paper":"https://pith.science/paper/HYUO4AKP"},"agent_actions":{"view_html":"https://pith.science/pith/HYUO4AKPOS24E7J64TVFRMPFJX","download_json":"https://pith.science/pith/HYUO4AKPOS24E7J64TVFRMPFJX.json","view_paper":"https://pith.science/paper/HYUO4AKP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.09891&json=true","fetch_graph":"https://pith.science/api/pith-number/HYUO4AKPOS24E7J64TVFRMPFJX/graph.json","fetch_events":"https://pith.science/api/pith-number/HYUO4AKPOS24E7J64TVFRMPFJX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HYUO4AKPOS24E7J64TVFRMPFJX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HYUO4AKPOS24E7J64TVFRMPFJX/action/storage_attestation","attest_author":"https://pith.science/pith/HYUO4AKPOS24E7J64TVFRMPFJX/action/author_attestation","sign_citation":"https://pith.science/pith/HYUO4AKPOS24E7J64TVFRMPFJX/action/citation_signature","submit_replication":"https://pith.science/pith/HYUO4AKPOS24E7J64TVFRMPFJX/action/replication_record"}},"created_at":"2026-05-17T23:50:36.090961+00:00","updated_at":"2026-05-17T23:50:36.090961+00:00"}