{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:IVFWM3TP6UF5IHRPZV6HZ4EGSZ","short_pith_number":"pith:IVFWM3TP","schema_version":"1.0","canonical_sha256":"454b666e6ff50bd41e2fcd7c7cf086966f927426ede0f1843b4217844596869c","source":{"kind":"arxiv","id":"2106.03112","version":1},"attestation_state":"computed","paper":{"title":"Rethinking Training from Scratch for Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hong Zhang, Yang Li, Yu Zhang","submitted_at":"2021-06-06T13:05:57Z","abstract_excerpt":"The ImageNet pre-training initialization is the de-facto standard for object detection. He et al. found it is possible to train detector from scratch(random initialization) while needing a longer training schedule with proper normalization technique. In this paper, we explore to directly pre-training on target dataset for object detection. Under this situation, we discover that the widely adopted large resizing strategy e.g. resize image to (1333, 800) is important for fine-tuning but it's not necessary for pre-training. Specifically, we propose a new training pipeline for object detection tha"},"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":"2106.03112","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-06T13:05:57Z","cross_cats_sorted":[],"title_canon_sha256":"c44db3ae932571d4b20b865098d9ae43e74c41ea94334ea6f002c7c683871729","abstract_canon_sha256":"6026cfd6501dd17faa95105d06bf9b6a8f768961a0805caadbcfba89205564f6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:46:33.942859Z","signature_b64":"2OoAcd0DJHBUVMpKtYAeP7creqW1chz26E5bJg/VrzJnqO0yFaFWCy/zP6vJOaxKvrQLZ8/Ca01A8KbpdLZ6DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"454b666e6ff50bd41e2fcd7c7cf086966f927426ede0f1843b4217844596869c","last_reissued_at":"2026-07-05T02:46:33.942461Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:46:33.942461Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Training from Scratch for Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hong Zhang, Yang Li, Yu Zhang","submitted_at":"2021-06-06T13:05:57Z","abstract_excerpt":"The ImageNet pre-training initialization is the de-facto standard for object detection. He et al. found it is possible to train detector from scratch(random initialization) while needing a longer training schedule with proper normalization technique. In this paper, we explore to directly pre-training on target dataset for object detection. Under this situation, we discover that the widely adopted large resizing strategy e.g. resize image to (1333, 800) is important for fine-tuning but it's not necessary for pre-training. Specifically, we propose a new training pipeline for object detection tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.03112","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/2106.03112/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":"2106.03112","created_at":"2026-07-05T02:46:33.942524+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.03112v1","created_at":"2026-07-05T02:46:33.942524+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.03112","created_at":"2026-07-05T02:46:33.942524+00:00"},{"alias_kind":"pith_short_12","alias_value":"IVFWM3TP6UF5","created_at":"2026-07-05T02:46:33.942524+00:00"},{"alias_kind":"pith_short_16","alias_value":"IVFWM3TP6UF5IHRP","created_at":"2026-07-05T02:46:33.942524+00:00"},{"alias_kind":"pith_short_8","alias_value":"IVFWM3TP","created_at":"2026-07-05T02:46:33.942524+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/IVFWM3TP6UF5IHRPZV6HZ4EGSZ","json":"https://pith.science/pith/IVFWM3TP6UF5IHRPZV6HZ4EGSZ.json","graph_json":"https://pith.science/api/pith-number/IVFWM3TP6UF5IHRPZV6HZ4EGSZ/graph.json","events_json":"https://pith.science/api/pith-number/IVFWM3TP6UF5IHRPZV6HZ4EGSZ/events.json","paper":"https://pith.science/paper/IVFWM3TP"},"agent_actions":{"view_html":"https://pith.science/pith/IVFWM3TP6UF5IHRPZV6HZ4EGSZ","download_json":"https://pith.science/pith/IVFWM3TP6UF5IHRPZV6HZ4EGSZ.json","view_paper":"https://pith.science/paper/IVFWM3TP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.03112&json=true","fetch_graph":"https://pith.science/api/pith-number/IVFWM3TP6UF5IHRPZV6HZ4EGSZ/graph.json","fetch_events":"https://pith.science/api/pith-number/IVFWM3TP6UF5IHRPZV6HZ4EGSZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IVFWM3TP6UF5IHRPZV6HZ4EGSZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IVFWM3TP6UF5IHRPZV6HZ4EGSZ/action/storage_attestation","attest_author":"https://pith.science/pith/IVFWM3TP6UF5IHRPZV6HZ4EGSZ/action/author_attestation","sign_citation":"https://pith.science/pith/IVFWM3TP6UF5IHRPZV6HZ4EGSZ/action/citation_signature","submit_replication":"https://pith.science/pith/IVFWM3TP6UF5IHRPZV6HZ4EGSZ/action/replication_record"}},"created_at":"2026-07-05T02:46:33.942524+00:00","updated_at":"2026-07-05T02:46:33.942524+00:00"}