{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:7LTODBV6H2UZV72Q2HA2F7LI5U","short_pith_number":"pith:7LTODBV6","schema_version":"1.0","canonical_sha256":"fae6e186be3ea99aff50d1c1a2fd68ed08d4c8f63186cd907555c46673e35278","source":{"kind":"arxiv","id":"1711.07240","version":4},"attestation_state":"computed","paper":{"title":"MegDet: A Large Mini-Batch Object Detector","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Peng, Gang Yu, Jian Sun, Kai Jia, Tete Xiao, Xiangyu Zhang, Yuning Jiang, Zeming Li","submitted_at":"2017-11-20T10:16:33Z","abstract_excerpt":"The improvements in recent CNN-based object detection works, from R-CNN [11], Fast/Faster R-CNN [10, 31] to recent Mask R-CNN [14] and RetinaNet [24], mainly come from new network, new framework, or novel loss design. But mini-batch size, a key factor in the training, has not been well studied. In this paper, we propose a Large MiniBatch Object Detector (MegDet) to enable the training with much larger mini-batch size than before (e.g. from 16 to 256), so that we can effectively utilize multiple GPUs (up to 128 in our experiments) to significantly shorten the training time. Technically, we sugg"},"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":"1711.07240","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-20T10:16:33Z","cross_cats_sorted":[],"title_canon_sha256":"4c24e5e957e9002bcc78fabd835b40c9f01c30e9699232aec9c0e1e4865ec08a","abstract_canon_sha256":"6afc2152714078183584a992ef663df4a8fc68f521c583f3fb03b632fbeb4ef0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:18:46.049734Z","signature_b64":"+YPTABaLSLBFv5ImGkk6cmwIhDT8W33HSVm/V3BBu6dAjigIcD6JOMSDPjxE/Xac6sCC54gcO6iebDgkCGnEAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fae6e186be3ea99aff50d1c1a2fd68ed08d4c8f63186cd907555c46673e35278","last_reissued_at":"2026-05-18T00:18:46.049151Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:18:46.049151Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MegDet: A Large Mini-Batch Object Detector","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Peng, Gang Yu, Jian Sun, Kai Jia, Tete Xiao, Xiangyu Zhang, Yuning Jiang, Zeming Li","submitted_at":"2017-11-20T10:16:33Z","abstract_excerpt":"The improvements in recent CNN-based object detection works, from R-CNN [11], Fast/Faster R-CNN [10, 31] to recent Mask R-CNN [14] and RetinaNet [24], mainly come from new network, new framework, or novel loss design. But mini-batch size, a key factor in the training, has not been well studied. In this paper, we propose a Large MiniBatch Object Detector (MegDet) to enable the training with much larger mini-batch size than before (e.g. from 16 to 256), so that we can effectively utilize multiple GPUs (up to 128 in our experiments) to significantly shorten the training time. Technically, we sugg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.07240","kind":"arxiv","version":4},"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":"1711.07240","created_at":"2026-05-18T00:18:46.049230+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.07240v4","created_at":"2026-05-18T00:18:46.049230+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.07240","created_at":"2026-05-18T00:18:46.049230+00:00"},{"alias_kind":"pith_short_12","alias_value":"7LTODBV6H2UZ","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_16","alias_value":"7LTODBV6H2UZV72Q","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_8","alias_value":"7LTODBV6","created_at":"2026-05-18T12:31:05.417338+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/7LTODBV6H2UZV72Q2HA2F7LI5U","json":"https://pith.science/pith/7LTODBV6H2UZV72Q2HA2F7LI5U.json","graph_json":"https://pith.science/api/pith-number/7LTODBV6H2UZV72Q2HA2F7LI5U/graph.json","events_json":"https://pith.science/api/pith-number/7LTODBV6H2UZV72Q2HA2F7LI5U/events.json","paper":"https://pith.science/paper/7LTODBV6"},"agent_actions":{"view_html":"https://pith.science/pith/7LTODBV6H2UZV72Q2HA2F7LI5U","download_json":"https://pith.science/pith/7LTODBV6H2UZV72Q2HA2F7LI5U.json","view_paper":"https://pith.science/paper/7LTODBV6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.07240&json=true","fetch_graph":"https://pith.science/api/pith-number/7LTODBV6H2UZV72Q2HA2F7LI5U/graph.json","fetch_events":"https://pith.science/api/pith-number/7LTODBV6H2UZV72Q2HA2F7LI5U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7LTODBV6H2UZV72Q2HA2F7LI5U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7LTODBV6H2UZV72Q2HA2F7LI5U/action/storage_attestation","attest_author":"https://pith.science/pith/7LTODBV6H2UZV72Q2HA2F7LI5U/action/author_attestation","sign_citation":"https://pith.science/pith/7LTODBV6H2UZV72Q2HA2F7LI5U/action/citation_signature","submit_replication":"https://pith.science/pith/7LTODBV6H2UZV72Q2HA2F7LI5U/action/replication_record"}},"created_at":"2026-05-18T00:18:46.049230+00:00","updated_at":"2026-05-18T00:18:46.049230+00:00"}