{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:LKVKMQ56P464ZK67N6LCOOJ2DT","short_pith_number":"pith:LKVKMQ56","schema_version":"1.0","canonical_sha256":"5aaaa643be7f3dccabdf6f9627393a1cd25f2302c4f2b771e9cd2ccc8f909a15","source":{"kind":"arxiv","id":"2103.13886","version":2},"attestation_state":"computed","paper":{"title":"Robust and Accurate Object Detection via Adversarial Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Boqing Gong, Cho-Jui Hsieh, Cihang Xie, Li Zhang, Mingxing Tan, Xiangning Chen","submitted_at":"2021-03-23T19:45:26Z","abstract_excerpt":"Data augmentation has become a de facto component for training high-performance deep image classifiers, but its potential is under-explored for object detection. Noting that most state-of-the-art object detectors benefit from fine-tuning a pre-trained classifier, we first study how the classifiers' gains from various data augmentations transfer to object detection. The results are discouraging; the gains diminish after fine-tuning in terms of either accuracy or robustness. This work instead augments the fine-tuning stage for object detectors by exploring adversarial examples, which can be view"},"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":"2103.13886","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-23T19:45:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"eb22fd541d1c632ea50f019d8bc4ea26255ff31fdc966b16932f0a5fcbbaab82","abstract_canon_sha256":"45353d0c776838fa54a2ae7ed70ed3e1b834a291ef78d99ee3a8e2395825e61a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:26:57.722383Z","signature_b64":"fe4ZDUpJyZB4eh8FYQtOw33PQjHFXBip1pxAbwxg1HQhJqI2GWOyIJxZUaJ3aZGVJaNz7xOJk1gKVNnsSZO6Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5aaaa643be7f3dccabdf6f9627393a1cd25f2302c4f2b771e9cd2ccc8f909a15","last_reissued_at":"2026-07-05T02:26:57.721920Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:26:57.721920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust and Accurate Object Detection via Adversarial Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Boqing Gong, Cho-Jui Hsieh, Cihang Xie, Li Zhang, Mingxing Tan, Xiangning Chen","submitted_at":"2021-03-23T19:45:26Z","abstract_excerpt":"Data augmentation has become a de facto component for training high-performance deep image classifiers, but its potential is under-explored for object detection. Noting that most state-of-the-art object detectors benefit from fine-tuning a pre-trained classifier, we first study how the classifiers' gains from various data augmentations transfer to object detection. The results are discouraging; the gains diminish after fine-tuning in terms of either accuracy or robustness. This work instead augments the fine-tuning stage for object detectors by exploring adversarial examples, which can be view"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.13886","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2103.13886/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":"2103.13886","created_at":"2026-07-05T02:26:57.721978+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.13886v2","created_at":"2026-07-05T02:26:57.721978+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.13886","created_at":"2026-07-05T02:26:57.721978+00:00"},{"alias_kind":"pith_short_12","alias_value":"LKVKMQ56P464","created_at":"2026-07-05T02:26:57.721978+00:00"},{"alias_kind":"pith_short_16","alias_value":"LKVKMQ56P464ZK67","created_at":"2026-07-05T02:26:57.721978+00:00"},{"alias_kind":"pith_short_8","alias_value":"LKVKMQ56","created_at":"2026-07-05T02:26:57.721978+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/LKVKMQ56P464ZK67N6LCOOJ2DT","json":"https://pith.science/pith/LKVKMQ56P464ZK67N6LCOOJ2DT.json","graph_json":"https://pith.science/api/pith-number/LKVKMQ56P464ZK67N6LCOOJ2DT/graph.json","events_json":"https://pith.science/api/pith-number/LKVKMQ56P464ZK67N6LCOOJ2DT/events.json","paper":"https://pith.science/paper/LKVKMQ56"},"agent_actions":{"view_html":"https://pith.science/pith/LKVKMQ56P464ZK67N6LCOOJ2DT","download_json":"https://pith.science/pith/LKVKMQ56P464ZK67N6LCOOJ2DT.json","view_paper":"https://pith.science/paper/LKVKMQ56","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.13886&json=true","fetch_graph":"https://pith.science/api/pith-number/LKVKMQ56P464ZK67N6LCOOJ2DT/graph.json","fetch_events":"https://pith.science/api/pith-number/LKVKMQ56P464ZK67N6LCOOJ2DT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LKVKMQ56P464ZK67N6LCOOJ2DT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LKVKMQ56P464ZK67N6LCOOJ2DT/action/storage_attestation","attest_author":"https://pith.science/pith/LKVKMQ56P464ZK67N6LCOOJ2DT/action/author_attestation","sign_citation":"https://pith.science/pith/LKVKMQ56P464ZK67N6LCOOJ2DT/action/citation_signature","submit_replication":"https://pith.science/pith/LKVKMQ56P464ZK67N6LCOOJ2DT/action/replication_record"}},"created_at":"2026-07-05T02:26:57.721978+00:00","updated_at":"2026-07-05T02:26:57.721978+00:00"}