{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:VHQMGZAUGM3F44LEQBUCBND7LW","short_pith_number":"pith:VHQMGZAU","schema_version":"1.0","canonical_sha256":"a9e0c3641433365e7164806820b47f5d95e42b3613c7adf6870f6172890eae9c","source":{"kind":"arxiv","id":"1708.04896","version":2},"attestation_state":"computed","paper":{"title":"Random Erasing Data Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guoliang Kang, Liang Zheng, Shaozi Li, Yi Yang, Zhun Zhong","submitted_at":"2017-08-16T13:56:48Z","abstract_excerpt":"In this paper, we introduce Random Erasing, a new data augmentation method for training the convolutional neural network (CNN). In training, Random Erasing randomly selects a rectangle region in an image and erases its pixels with random values. In this process, training images with various levels of occlusion are generated, which reduces the risk of over-fitting and makes the model robust to occlusion. Random Erasing is parameter learning free, easy to implement, and can be integrated with most of the CNN-based recognition models. Albeit simple, Random Erasing is complementary to commonly use"},"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":"1708.04896","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-16T13:56:48Z","cross_cats_sorted":[],"title_canon_sha256":"39ab79150ffd14bcff157d8c7d74fe0f6bae378f3704f2c3c9b3439d57dc184c","abstract_canon_sha256":"cc6950f5cdf21abf806f125cd132181eb2f1c921fbe6a57d6c4fff6c2e487133"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:30:27.917878Z","signature_b64":"BMydLyhxKZIzQ67PIz1CVAvmXEYQDNfVpOmI74Ex0oYdfRYhTVcXAapRWB9WsrT8AO/e8eZhe6c2hP33kvU8Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9e0c3641433365e7164806820b47f5d95e42b3613c7adf6870f6172890eae9c","last_reissued_at":"2026-05-18T00:30:27.917181Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:30:27.917181Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Random Erasing Data Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guoliang Kang, Liang Zheng, Shaozi Li, Yi Yang, Zhun Zhong","submitted_at":"2017-08-16T13:56:48Z","abstract_excerpt":"In this paper, we introduce Random Erasing, a new data augmentation method for training the convolutional neural network (CNN). In training, Random Erasing randomly selects a rectangle region in an image and erases its pixels with random values. In this process, training images with various levels of occlusion are generated, which reduces the risk of over-fitting and makes the model robust to occlusion. Random Erasing is parameter learning free, easy to implement, and can be integrated with most of the CNN-based recognition models. Albeit simple, Random Erasing is complementary to commonly use"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.04896","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":"1708.04896","created_at":"2026-05-18T00:30:27.917296+00:00"},{"alias_kind":"arxiv_version","alias_value":"1708.04896v2","created_at":"2026-05-18T00:30:27.917296+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.04896","created_at":"2026-05-18T00:30:27.917296+00:00"},{"alias_kind":"pith_short_12","alias_value":"VHQMGZAUGM3F","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_16","alias_value":"VHQMGZAUGM3F44LE","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_8","alias_value":"VHQMGZAU","created_at":"2026-05-18T12:31:49.984773+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":5,"sample":[{"citing_arxiv_id":"1906.10822","citing_title":"Gradient Noise Convolution (GNC): Smoothing Loss Function for Distributed Large-Batch SGD","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"1906.11172","citing_title":"Learning Data Augmentation Strategies for Object Detection","ref_index":53,"is_internal_anchor":true},{"citing_arxiv_id":"1906.11484","citing_title":"Automated Segmentation of Hip and Thigh Muscles in Metal Artifact-Contaminated CT using Convolutional Neural Network-Enhanced Normalized Metal Artifact Reduction","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"1907.03253","citing_title":"A Novel Teacher-Student Learning Framework For Occluded Person Re-Identification","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07379","citing_title":"RELO: Reinforcement Learning to Localize for Visual Object Tracking","ref_index":145,"is_internal_anchor":true},{"citing_arxiv_id":"2604.03803","citing_title":"R\\'enyi Attention Entropy for Patch Pruning","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2004.10934","citing_title":"YOLOv4: Optimal Speed and Accuracy of Object Detection","ref_index":100,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07379","citing_title":"RELO: Reinforcement Learning to Localize for Visual Object Tracking","ref_index":144,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VHQMGZAUGM3F44LEQBUCBND7LW","json":"https://pith.science/pith/VHQMGZAUGM3F44LEQBUCBND7LW.json","graph_json":"https://pith.science/api/pith-number/VHQMGZAUGM3F44LEQBUCBND7LW/graph.json","events_json":"https://pith.science/api/pith-number/VHQMGZAUGM3F44LEQBUCBND7LW/events.json","paper":"https://pith.science/paper/VHQMGZAU"},"agent_actions":{"view_html":"https://pith.science/pith/VHQMGZAUGM3F44LEQBUCBND7LW","download_json":"https://pith.science/pith/VHQMGZAUGM3F44LEQBUCBND7LW.json","view_paper":"https://pith.science/paper/VHQMGZAU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1708.04896&json=true","fetch_graph":"https://pith.science/api/pith-number/VHQMGZAUGM3F44LEQBUCBND7LW/graph.json","fetch_events":"https://pith.science/api/pith-number/VHQMGZAUGM3F44LEQBUCBND7LW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VHQMGZAUGM3F44LEQBUCBND7LW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VHQMGZAUGM3F44LEQBUCBND7LW/action/storage_attestation","attest_author":"https://pith.science/pith/VHQMGZAUGM3F44LEQBUCBND7LW/action/author_attestation","sign_citation":"https://pith.science/pith/VHQMGZAUGM3F44LEQBUCBND7LW/action/citation_signature","submit_replication":"https://pith.science/pith/VHQMGZAUGM3F44LEQBUCBND7LW/action/replication_record"}},"created_at":"2026-05-18T00:30:27.917296+00:00","updated_at":"2026-05-18T00:30:27.917296+00:00"}