{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XAYQM7EFYYPRIW3D3TEOLPH5O7","short_pith_number":"pith:XAYQM7EF","schema_version":"1.0","canonical_sha256":"b831067c85c61f145b63dcc8e5bcfd77ff8365969f704e926506759183e2bfc6","source":{"kind":"arxiv","id":"2304.03428","version":1},"attestation_state":"computed","paper":{"title":"TinyDet: Accurate Small Object Detection in Lightweight Generic Detectors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiemin Fang, Qian Zhang, Shaoyu Chen, Tianheng Cheng, Wenyu Liu, Xinggang Wang, Yuan Li","submitted_at":"2023-04-07T00:45:50Z","abstract_excerpt":"Small object detection requires the detection head to scan a large number of positions on image feature maps, which is extremely hard for computation- and energy-efficient lightweight generic detectors. To accurately detect small objects with limited computation, we propose a two-stage lightweight detection framework with extremely low computation complexity, termed as TinyDet. It enables high-resolution feature maps for dense anchoring to better cover small objects, proposes a sparsely-connected convolution for computation reduction, enhances the early stage features in the backbone, and addr"},"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":"2304.03428","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-07T00:45:50Z","cross_cats_sorted":[],"title_canon_sha256":"2f1b713d8cf52b4c778c22deed0c6c3ee4431497d95c9b884a70f8c4851580c7","abstract_canon_sha256":"18045bca9153bdb3f7e2acc1eaaaaafc398d937a9e84ed8beae028470d5dd776"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:58:55.770517Z","signature_b64":"apwxSIWIuH0+UiHXdTiM8RTfb32hqpuorp1thx86lka9bYBWS3I92YJv7+E4+cZLilzYNuyR/iCS1FWQUMgzAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b831067c85c61f145b63dcc8e5bcfd77ff8365969f704e926506759183e2bfc6","last_reissued_at":"2026-07-05T05:58:55.770109Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:58:55.770109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TinyDet: Accurate Small Object Detection in Lightweight Generic Detectors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiemin Fang, Qian Zhang, Shaoyu Chen, Tianheng Cheng, Wenyu Liu, Xinggang Wang, Yuan Li","submitted_at":"2023-04-07T00:45:50Z","abstract_excerpt":"Small object detection requires the detection head to scan a large number of positions on image feature maps, which is extremely hard for computation- and energy-efficient lightweight generic detectors. To accurately detect small objects with limited computation, we propose a two-stage lightweight detection framework with extremely low computation complexity, termed as TinyDet. It enables high-resolution feature maps for dense anchoring to better cover small objects, proposes a sparsely-connected convolution for computation reduction, enhances the early stage features in the backbone, and addr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.03428","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/2304.03428/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":"2304.03428","created_at":"2026-07-05T05:58:55.770165+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.03428v1","created_at":"2026-07-05T05:58:55.770165+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.03428","created_at":"2026-07-05T05:58:55.770165+00:00"},{"alias_kind":"pith_short_12","alias_value":"XAYQM7EFYYPR","created_at":"2026-07-05T05:58:55.770165+00:00"},{"alias_kind":"pith_short_16","alias_value":"XAYQM7EFYYPRIW3D","created_at":"2026-07-05T05:58:55.770165+00:00"},{"alias_kind":"pith_short_8","alias_value":"XAYQM7EF","created_at":"2026-07-05T05:58:55.770165+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.08339","citing_title":"SHeRL-FL: When Representation Learning Meets Split Learning in Hierarchical Federated Learning","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XAYQM7EFYYPRIW3D3TEOLPH5O7","json":"https://pith.science/pith/XAYQM7EFYYPRIW3D3TEOLPH5O7.json","graph_json":"https://pith.science/api/pith-number/XAYQM7EFYYPRIW3D3TEOLPH5O7/graph.json","events_json":"https://pith.science/api/pith-number/XAYQM7EFYYPRIW3D3TEOLPH5O7/events.json","paper":"https://pith.science/paper/XAYQM7EF"},"agent_actions":{"view_html":"https://pith.science/pith/XAYQM7EFYYPRIW3D3TEOLPH5O7","download_json":"https://pith.science/pith/XAYQM7EFYYPRIW3D3TEOLPH5O7.json","view_paper":"https://pith.science/paper/XAYQM7EF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.03428&json=true","fetch_graph":"https://pith.science/api/pith-number/XAYQM7EFYYPRIW3D3TEOLPH5O7/graph.json","fetch_events":"https://pith.science/api/pith-number/XAYQM7EFYYPRIW3D3TEOLPH5O7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XAYQM7EFYYPRIW3D3TEOLPH5O7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XAYQM7EFYYPRIW3D3TEOLPH5O7/action/storage_attestation","attest_author":"https://pith.science/pith/XAYQM7EFYYPRIW3D3TEOLPH5O7/action/author_attestation","sign_citation":"https://pith.science/pith/XAYQM7EFYYPRIW3D3TEOLPH5O7/action/citation_signature","submit_replication":"https://pith.science/pith/XAYQM7EFYYPRIW3D3TEOLPH5O7/action/replication_record"}},"created_at":"2026-07-05T05:58:55.770165+00:00","updated_at":"2026-07-05T05:58:55.770165+00:00"}