{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4FDXC33IDRI2STB6JRBG4L5SGR","short_pith_number":"pith:4FDXC33I","schema_version":"1.0","canonical_sha256":"e147716f681c51a94c3e4c426e2fb23454632024f7b579ae2c3a942fa9873194","source":{"kind":"arxiv","id":"2307.11528","version":1},"attestation_state":"computed","paper":{"title":"Improving Viewpoint Robustness for Visual Recognition via Adversarial Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hang Su, Jianteng Peng, Ning Chen, Shouwei Ruan, Xingxing Wei, Yinpeng Dong","submitted_at":"2023-07-21T12:18:35Z","abstract_excerpt":"Viewpoint invariance remains challenging for visual recognition in the 3D world, as altering the viewing directions can significantly impact predictions for the same object. While substantial efforts have been dedicated to making neural networks invariant to 2D image translations and rotations, viewpoint invariance is rarely investigated. Motivated by the success of adversarial training in enhancing model robustness, we propose Viewpoint-Invariant Adversarial Training (VIAT) to improve the viewpoint robustness of image classifiers. Regarding viewpoint transformation as an attack, we formulate "},"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":"2307.11528","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-21T12:18:35Z","cross_cats_sorted":[],"title_canon_sha256":"717a4863b8d0ecbb63508203ca4484e89bdb84d6b8168ad21cf46711f3e0f780","abstract_canon_sha256":"c379d5a002399158c76094e0e2c5aae763054a245a0cfba750b74ee75a72d755"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:33:28.791355Z","signature_b64":"6QpGDOiDP7iXzh0c8NwOoff++SyyQdCLTRfjS3YEZ9eKRq/bFkaQ7y0DtPUduYGdH70B6P9RFKrJWgDdcl3MAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e147716f681c51a94c3e4c426e2fb23454632024f7b579ae2c3a942fa9873194","last_reissued_at":"2026-07-05T06:33:28.790961Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:33:28.790961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Viewpoint Robustness for Visual Recognition via Adversarial Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hang Su, Jianteng Peng, Ning Chen, Shouwei Ruan, Xingxing Wei, Yinpeng Dong","submitted_at":"2023-07-21T12:18:35Z","abstract_excerpt":"Viewpoint invariance remains challenging for visual recognition in the 3D world, as altering the viewing directions can significantly impact predictions for the same object. While substantial efforts have been dedicated to making neural networks invariant to 2D image translations and rotations, viewpoint invariance is rarely investigated. Motivated by the success of adversarial training in enhancing model robustness, we propose Viewpoint-Invariant Adversarial Training (VIAT) to improve the viewpoint robustness of image classifiers. Regarding viewpoint transformation as an attack, we formulate "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.11528","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/2307.11528/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":"2307.11528","created_at":"2026-07-05T06:33:28.791017+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.11528v1","created_at":"2026-07-05T06:33:28.791017+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.11528","created_at":"2026-07-05T06:33:28.791017+00:00"},{"alias_kind":"pith_short_12","alias_value":"4FDXC33IDRI2","created_at":"2026-07-05T06:33:28.791017+00:00"},{"alias_kind":"pith_short_16","alias_value":"4FDXC33IDRI2STB6","created_at":"2026-07-05T06:33:28.791017+00:00"},{"alias_kind":"pith_short_8","alias_value":"4FDXC33I","created_at":"2026-07-05T06:33:28.791017+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.08611","citing_title":"Towards Class-wise Fair Adversarial Training via Anti-Bias Soft Label Distillation","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4FDXC33IDRI2STB6JRBG4L5SGR","json":"https://pith.science/pith/4FDXC33IDRI2STB6JRBG4L5SGR.json","graph_json":"https://pith.science/api/pith-number/4FDXC33IDRI2STB6JRBG4L5SGR/graph.json","events_json":"https://pith.science/api/pith-number/4FDXC33IDRI2STB6JRBG4L5SGR/events.json","paper":"https://pith.science/paper/4FDXC33I"},"agent_actions":{"view_html":"https://pith.science/pith/4FDXC33IDRI2STB6JRBG4L5SGR","download_json":"https://pith.science/pith/4FDXC33IDRI2STB6JRBG4L5SGR.json","view_paper":"https://pith.science/paper/4FDXC33I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.11528&json=true","fetch_graph":"https://pith.science/api/pith-number/4FDXC33IDRI2STB6JRBG4L5SGR/graph.json","fetch_events":"https://pith.science/api/pith-number/4FDXC33IDRI2STB6JRBG4L5SGR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4FDXC33IDRI2STB6JRBG4L5SGR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4FDXC33IDRI2STB6JRBG4L5SGR/action/storage_attestation","attest_author":"https://pith.science/pith/4FDXC33IDRI2STB6JRBG4L5SGR/action/author_attestation","sign_citation":"https://pith.science/pith/4FDXC33IDRI2STB6JRBG4L5SGR/action/citation_signature","submit_replication":"https://pith.science/pith/4FDXC33IDRI2STB6JRBG4L5SGR/action/replication_record"}},"created_at":"2026-07-05T06:33:28.791017+00:00","updated_at":"2026-07-05T06:33:28.791017+00:00"}