{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XY4BOEOGVHWNN6I7OCGOGFUQHY","short_pith_number":"pith:XY4BOEOG","schema_version":"1.0","canonical_sha256":"be381711c6a9ecd6f91f708ce316903e38b1091abcebc9fc0f8d9930e237efc0","source":{"kind":"arxiv","id":"2410.19635","version":1},"attestation_state":"computed","paper":{"title":"Frozen-DETR: Enhancing DETR with Image Understanding from Frozen Foundation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Junkai Yan, Qize Yang, Shenghao Fu, Wei-Shi Zheng, Xiaohua Xie, Xihan Wei","submitted_at":"2024-10-25T15:38:24Z","abstract_excerpt":"Recent vision foundation models can extract universal representations and show impressive abilities in various tasks. However, their application on object detection is largely overlooked, especially without fine-tuning them. In this work, we show that frozen foundation models can be a versatile feature enhancer, even though they are not pre-trained for object detection. Specifically, we explore directly transferring the high-level image understanding of foundation models to detectors in the following two ways. First, the class token in foundation models provides an in-depth understanding of th"},"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":"2410.19635","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-25T15:38:24Z","cross_cats_sorted":[],"title_canon_sha256":"61afec061676d5a99ec42288c9405f5abe6d564dedb2761412b5082e1bfd3300","abstract_canon_sha256":"f176b53c428a4ec8bfdb70997697e7789123d91e99ccd4eb2ece495929d4757c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:25:59.543955Z","signature_b64":"+6v/QjFM4G91EHYCNPb53rEUZYX4gLIvWZXM/QXpvmiLGucR+MCZzoOE/TEK720J0syHck3HJWGIeQTOMB6RCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be381711c6a9ecd6f91f708ce316903e38b1091abcebc9fc0f8d9930e237efc0","last_reissued_at":"2026-07-05T09:25:59.543484Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:25:59.543484Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Frozen-DETR: Enhancing DETR with Image Understanding from Frozen Foundation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Junkai Yan, Qize Yang, Shenghao Fu, Wei-Shi Zheng, Xiaohua Xie, Xihan Wei","submitted_at":"2024-10-25T15:38:24Z","abstract_excerpt":"Recent vision foundation models can extract universal representations and show impressive abilities in various tasks. However, their application on object detection is largely overlooked, especially without fine-tuning them. In this work, we show that frozen foundation models can be a versatile feature enhancer, even though they are not pre-trained for object detection. Specifically, we explore directly transferring the high-level image understanding of foundation models to detectors in the following two ways. First, the class token in foundation models provides an in-depth understanding of th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.19635","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/2410.19635/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":"2410.19635","created_at":"2026-07-05T09:25:59.543545+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.19635v1","created_at":"2026-07-05T09:25:59.543545+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.19635","created_at":"2026-07-05T09:25:59.543545+00:00"},{"alias_kind":"pith_short_12","alias_value":"XY4BOEOGVHWN","created_at":"2026-07-05T09:25:59.543545+00:00"},{"alias_kind":"pith_short_16","alias_value":"XY4BOEOGVHWNN6I7","created_at":"2026-07-05T09:25:59.543545+00:00"},{"alias_kind":"pith_short_8","alias_value":"XY4BOEOG","created_at":"2026-07-05T09:25:59.543545+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/XY4BOEOGVHWNN6I7OCGOGFUQHY","json":"https://pith.science/pith/XY4BOEOGVHWNN6I7OCGOGFUQHY.json","graph_json":"https://pith.science/api/pith-number/XY4BOEOGVHWNN6I7OCGOGFUQHY/graph.json","events_json":"https://pith.science/api/pith-number/XY4BOEOGVHWNN6I7OCGOGFUQHY/events.json","paper":"https://pith.science/paper/XY4BOEOG"},"agent_actions":{"view_html":"https://pith.science/pith/XY4BOEOGVHWNN6I7OCGOGFUQHY","download_json":"https://pith.science/pith/XY4BOEOGVHWNN6I7OCGOGFUQHY.json","view_paper":"https://pith.science/paper/XY4BOEOG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.19635&json=true","fetch_graph":"https://pith.science/api/pith-number/XY4BOEOGVHWNN6I7OCGOGFUQHY/graph.json","fetch_events":"https://pith.science/api/pith-number/XY4BOEOGVHWNN6I7OCGOGFUQHY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XY4BOEOGVHWNN6I7OCGOGFUQHY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XY4BOEOGVHWNN6I7OCGOGFUQHY/action/storage_attestation","attest_author":"https://pith.science/pith/XY4BOEOGVHWNN6I7OCGOGFUQHY/action/author_attestation","sign_citation":"https://pith.science/pith/XY4BOEOGVHWNN6I7OCGOGFUQHY/action/citation_signature","submit_replication":"https://pith.science/pith/XY4BOEOGVHWNN6I7OCGOGFUQHY/action/replication_record"}},"created_at":"2026-07-05T09:25:59.543545+00:00","updated_at":"2026-07-05T09:25:59.543545+00:00"}