{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:XXAXC565MKHQ4FWNJBSCGEYS3J","short_pith_number":"pith:XXAXC565","schema_version":"1.0","canonical_sha256":"bdc17177dd628f0e16cd4864231312da48cae7c77d44e9c58190ccb724c697a9","source":{"kind":"arxiv","id":"1809.09294","version":2},"attestation_state":"computed","paper":{"title":"Object Detection from Scratch with Deep Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianguo Li, Xiangyang Xue, Yu-Gang Jiang, Yurong Chen, Zhiqiang Shen, Zhuang Liu","submitted_at":"2018-09-25T02:56:44Z","abstract_excerpt":"We propose Deeply Supervised Object Detectors (DSOD), an object detection framework that can be trained from scratch. Recent advances in object detection heavily depend on the off-the-shelf models pre-trained on large-scale classification datasets like ImageNet and OpenImage. However, one problem is that adopting pre-trained models from classification to detection task may incur learning bias due to the different objective function and diverse distributions of object categories. Techniques like fine-tuning on detection task could alleviate this issue to some extent but are still not fundamenta"},"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":"1809.09294","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-09-25T02:56:44Z","cross_cats_sorted":[],"title_canon_sha256":"d1288524a79ed04d2f8c2ca301c9b0113fd288fa00e3d43f6958bbdbfc8439c2","abstract_canon_sha256":"28984e1da39516e6efffcabdfd6fb8fba793fa9949515e220aab2481773cc238"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:50:59.297704Z","signature_b64":"d8Zyn0wlMgD6grqTrARno3CLk1F6VdmTuLL28Br5RwxlYLlkNCjPlmLr89O8Je1o7kJSPOFRDHkafF7XWJiiBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bdc17177dd628f0e16cd4864231312da48cae7c77d44e9c58190ccb724c697a9","last_reissued_at":"2026-05-17T23:50:59.296867Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:50:59.296867Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Object Detection from Scratch with Deep Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianguo Li, Xiangyang Xue, Yu-Gang Jiang, Yurong Chen, Zhiqiang Shen, Zhuang Liu","submitted_at":"2018-09-25T02:56:44Z","abstract_excerpt":"We propose Deeply Supervised Object Detectors (DSOD), an object detection framework that can be trained from scratch. Recent advances in object detection heavily depend on the off-the-shelf models pre-trained on large-scale classification datasets like ImageNet and OpenImage. However, one problem is that adopting pre-trained models from classification to detection task may incur learning bias due to the different objective function and diverse distributions of object categories. Techniques like fine-tuning on detection task could alleviate this issue to some extent but are still not fundamenta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.09294","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":"1809.09294","created_at":"2026-05-17T23:50:59.297013+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.09294v2","created_at":"2026-05-17T23:50:59.297013+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.09294","created_at":"2026-05-17T23:50:59.297013+00:00"},{"alias_kind":"pith_short_12","alias_value":"XXAXC565MKHQ","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_16","alias_value":"XXAXC565MKHQ4FWN","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_8","alias_value":"XXAXC565","created_at":"2026-05-18T12:33:04.347982+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/XXAXC565MKHQ4FWNJBSCGEYS3J","json":"https://pith.science/pith/XXAXC565MKHQ4FWNJBSCGEYS3J.json","graph_json":"https://pith.science/api/pith-number/XXAXC565MKHQ4FWNJBSCGEYS3J/graph.json","events_json":"https://pith.science/api/pith-number/XXAXC565MKHQ4FWNJBSCGEYS3J/events.json","paper":"https://pith.science/paper/XXAXC565"},"agent_actions":{"view_html":"https://pith.science/pith/XXAXC565MKHQ4FWNJBSCGEYS3J","download_json":"https://pith.science/pith/XXAXC565MKHQ4FWNJBSCGEYS3J.json","view_paper":"https://pith.science/paper/XXAXC565","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.09294&json=true","fetch_graph":"https://pith.science/api/pith-number/XXAXC565MKHQ4FWNJBSCGEYS3J/graph.json","fetch_events":"https://pith.science/api/pith-number/XXAXC565MKHQ4FWNJBSCGEYS3J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XXAXC565MKHQ4FWNJBSCGEYS3J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XXAXC565MKHQ4FWNJBSCGEYS3J/action/storage_attestation","attest_author":"https://pith.science/pith/XXAXC565MKHQ4FWNJBSCGEYS3J/action/author_attestation","sign_citation":"https://pith.science/pith/XXAXC565MKHQ4FWNJBSCGEYS3J/action/citation_signature","submit_replication":"https://pith.science/pith/XXAXC565MKHQ4FWNJBSCGEYS3J/action/replication_record"}},"created_at":"2026-05-17T23:50:59.297013+00:00","updated_at":"2026-05-17T23:50:59.297013+00:00"}