{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:E6EKRXPN4PLYJVLLHGMCVXDDLY","short_pith_number":"pith:E6EKRXPN","schema_version":"1.0","canonical_sha256":"2788a8ddede3d784d56b39982adc635e3a3c811e2702aedf0ac41a4ae7c85f80","source":{"kind":"arxiv","id":"2001.04086","version":3},"attestation_state":"computed","paper":{"title":"GridMask Data Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hengshuang Zhao, Jiaya Jia, Pengguang Chen, Shu Liu, Xingquan Wang","submitted_at":"2020-01-13T07:27:05Z","abstract_excerpt":"We propose a novel data augmentation method `GridMask' in this paper. It utilizes information removal to achieve state-of-the-art results in a variety of computer vision tasks. We analyze the requirement of information dropping. Then we show limitation of existing information dropping algorithms and propose our structured method, which is simple and yet very effective. It is based on the deletion of regions of the input image. Our extensive experiments show that our method outperforms the latest AutoAugment, which is way more computationally expensive due to the use of reinforcement learning t"},"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":"2001.04086","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-01-13T07:27:05Z","cross_cats_sorted":[],"title_canon_sha256":"582b0196fe534aeb3b217dd63c6f56788863733738b75dc2b8abdb75065b1279","abstract_canon_sha256":"5b3364e4797846bd696495f21cddcfd921af14ff4ae307324ce784c03db19431"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:39:54.083969Z","signature_b64":"fITeKqWZSA6dhGy2VeWGuSENDijbDHKHlyEe26zyENmez9e9m9ruGsnwdgOCpwhfk5QY/k2LYhB3OvtC7oLnDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2788a8ddede3d784d56b39982adc635e3a3c811e2702aedf0ac41a4ae7c85f80","last_reissued_at":"2026-07-05T07:39:54.083552Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:39:54.083552Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GridMask Data Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hengshuang Zhao, Jiaya Jia, Pengguang Chen, Shu Liu, Xingquan Wang","submitted_at":"2020-01-13T07:27:05Z","abstract_excerpt":"We propose a novel data augmentation method `GridMask' in this paper. It utilizes information removal to achieve state-of-the-art results in a variety of computer vision tasks. We analyze the requirement of information dropping. Then we show limitation of existing information dropping algorithms and propose our structured method, which is simple and yet very effective. It is based on the deletion of regions of the input image. Our extensive experiments show that our method outperforms the latest AutoAugment, which is way more computationally expensive due to the use of reinforcement learning t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.04086","kind":"arxiv","version":3},"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/2001.04086/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":"2001.04086","created_at":"2026-07-05T07:39:54.083613+00:00"},{"alias_kind":"arxiv_version","alias_value":"2001.04086v3","created_at":"2026-07-05T07:39:54.083613+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.04086","created_at":"2026-07-05T07:39:54.083613+00:00"},{"alias_kind":"pith_short_12","alias_value":"E6EKRXPN4PLY","created_at":"2026-07-05T07:39:54.083613+00:00"},{"alias_kind":"pith_short_16","alias_value":"E6EKRXPN4PLYJVLL","created_at":"2026-07-05T07:39:54.083613+00:00"},{"alias_kind":"pith_short_8","alias_value":"E6EKRXPN","created_at":"2026-07-05T07:39:54.083613+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.02271","citing_title":"AGVBench: A Reliability-Oriented Benchmark of Data Augmentation for Vein Recognition","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30577","citing_title":"APRIL-MedSeg: A Modular Medical Image Segmentation Toolbox Embracing Modern Paradigms","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2004.10934","citing_title":"YOLOv4: Optimal Speed and Accuracy of Object Detection","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25405","citing_title":"Leveraging Previous-Traversal Point Cloud Map Priors for Camera-Based 3D Object Detection and Tracking","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E6EKRXPN4PLYJVLLHGMCVXDDLY","json":"https://pith.science/pith/E6EKRXPN4PLYJVLLHGMCVXDDLY.json","graph_json":"https://pith.science/api/pith-number/E6EKRXPN4PLYJVLLHGMCVXDDLY/graph.json","events_json":"https://pith.science/api/pith-number/E6EKRXPN4PLYJVLLHGMCVXDDLY/events.json","paper":"https://pith.science/paper/E6EKRXPN"},"agent_actions":{"view_html":"https://pith.science/pith/E6EKRXPN4PLYJVLLHGMCVXDDLY","download_json":"https://pith.science/pith/E6EKRXPN4PLYJVLLHGMCVXDDLY.json","view_paper":"https://pith.science/paper/E6EKRXPN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2001.04086&json=true","fetch_graph":"https://pith.science/api/pith-number/E6EKRXPN4PLYJVLLHGMCVXDDLY/graph.json","fetch_events":"https://pith.science/api/pith-number/E6EKRXPN4PLYJVLLHGMCVXDDLY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E6EKRXPN4PLYJVLLHGMCVXDDLY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E6EKRXPN4PLYJVLLHGMCVXDDLY/action/storage_attestation","attest_author":"https://pith.science/pith/E6EKRXPN4PLYJVLLHGMCVXDDLY/action/author_attestation","sign_citation":"https://pith.science/pith/E6EKRXPN4PLYJVLLHGMCVXDDLY/action/citation_signature","submit_replication":"https://pith.science/pith/E6EKRXPN4PLYJVLLHGMCVXDDLY/action/replication_record"}},"created_at":"2026-07-05T07:39:54.083613+00:00","updated_at":"2026-07-05T07:39:54.083613+00:00"}