{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:CXLO44IRDJC4NLD2S5MXB5AAYE","short_pith_number":"pith:CXLO44IR","schema_version":"1.0","canonical_sha256":"15d6ee71111a45c6ac7a975970f400c10e2b158c09fc342f3edeced004d86c8b","source":{"kind":"arxiv","id":"1909.00700","version":3},"attestation_state":"computed","paper":{"title":"Training-Time-Friendly Network for Real-Time Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Deng Cai, Guodong Xu, Haifeng Liu, Tu Zheng, Zheng Yang, Zili Liu","submitted_at":"2019-09-02T12:59:18Z","abstract_excerpt":"Modern object detectors can rarely achieve short training time, fast inference speed, and high accuracy at the same time. To strike a balance among them, we propose the Training-Time-Friendly Network (TTFNet). In this work, we start with light-head, single-stage, and anchor-free designs, which enable fast inference speed. Then, we focus on shortening training time. We notice that encoding more training samples from annotated boxes plays a similar role as increasing batch size, which helps enlarge the learning rate and accelerate the training process. To this end, we introduce a novel approach "},"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":"1909.00700","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-09-02T12:59:18Z","cross_cats_sorted":["cs.LG","eess.IV"],"title_canon_sha256":"dfcdf162fd6506c894eb0683049998c2c74c9a9a2aa17fc141db2f4485914931","abstract_canon_sha256":"981cc071fe660995e9c5823636e000b398043b09f6c6f5812cad045368c0767c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:21:36.498182Z","signature_b64":"fgQBEUYhwLb1OzTPCDCSXfQ+OaFddDALqlvnBXvt3Y2FOYSEN108bWQf+TVC0YcstrojdMkm0KDrcunhWGonAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15d6ee71111a45c6ac7a975970f400c10e2b158c09fc342f3edeced004d86c8b","last_reissued_at":"2026-07-05T00:21:36.497647Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:21:36.497647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training-Time-Friendly Network for Real-Time Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Deng Cai, Guodong Xu, Haifeng Liu, Tu Zheng, Zheng Yang, Zili Liu","submitted_at":"2019-09-02T12:59:18Z","abstract_excerpt":"Modern object detectors can rarely achieve short training time, fast inference speed, and high accuracy at the same time. To strike a balance among them, we propose the Training-Time-Friendly Network (TTFNet). In this work, we start with light-head, single-stage, and anchor-free designs, which enable fast inference speed. Then, we focus on shortening training time. We notice that encoding more training samples from annotated boxes plays a similar role as increasing batch size, which helps enlarge the learning rate and accelerate the training process. To this end, we introduce a novel approach "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.00700","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/1909.00700/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":"1909.00700","created_at":"2026-07-05T00:21:36.497744+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.00700v3","created_at":"2026-07-05T00:21:36.497744+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.00700","created_at":"2026-07-05T00:21:36.497744+00:00"},{"alias_kind":"pith_short_12","alias_value":"CXLO44IRDJC4","created_at":"2026-07-05T00:21:36.497744+00:00"},{"alias_kind":"pith_short_16","alias_value":"CXLO44IRDJC4NLD2","created_at":"2026-07-05T00:21:36.497744+00:00"},{"alias_kind":"pith_short_8","alias_value":"CXLO44IR","created_at":"2026-07-05T00:21:36.497744+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/CXLO44IRDJC4NLD2S5MXB5AAYE","json":"https://pith.science/pith/CXLO44IRDJC4NLD2S5MXB5AAYE.json","graph_json":"https://pith.science/api/pith-number/CXLO44IRDJC4NLD2S5MXB5AAYE/graph.json","events_json":"https://pith.science/api/pith-number/CXLO44IRDJC4NLD2S5MXB5AAYE/events.json","paper":"https://pith.science/paper/CXLO44IR"},"agent_actions":{"view_html":"https://pith.science/pith/CXLO44IRDJC4NLD2S5MXB5AAYE","download_json":"https://pith.science/pith/CXLO44IRDJC4NLD2S5MXB5AAYE.json","view_paper":"https://pith.science/paper/CXLO44IR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.00700&json=true","fetch_graph":"https://pith.science/api/pith-number/CXLO44IRDJC4NLD2S5MXB5AAYE/graph.json","fetch_events":"https://pith.science/api/pith-number/CXLO44IRDJC4NLD2S5MXB5AAYE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CXLO44IRDJC4NLD2S5MXB5AAYE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CXLO44IRDJC4NLD2S5MXB5AAYE/action/storage_attestation","attest_author":"https://pith.science/pith/CXLO44IRDJC4NLD2S5MXB5AAYE/action/author_attestation","sign_citation":"https://pith.science/pith/CXLO44IRDJC4NLD2S5MXB5AAYE/action/citation_signature","submit_replication":"https://pith.science/pith/CXLO44IRDJC4NLD2S5MXB5AAYE/action/replication_record"}},"created_at":"2026-07-05T00:21:36.497744+00:00","updated_at":"2026-07-05T00:21:36.497744+00:00"}