{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:IGY5WSB3X3DLH242AI4E2KRWQD","short_pith_number":"pith:IGY5WSB3","schema_version":"1.0","canonical_sha256":"41b1db483bbec6b3eb9a02384d2a3680d3c49346cd76cb7e2190a0278855de2d","source":{"kind":"arxiv","id":"2205.06230","version":2},"attestation_state":"computed","paper":{"title":"Simple Open-Vocabulary Object Detection with Vision Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexey Dosovitskiy, Alexey Gritsenko, Anurag Arnab, Aravindh Mahendran, Austin Stone, Dirk Weissenborn, Matthias Minderer, Maxim Neumann, Mostafa Dehghani, Neil Houlsby, Thomas Kipf, Xiaohua Zhai, Xiao Wang, Zhuoran Shen","submitted_at":"2022-05-12T17:20:36Z","abstract_excerpt":"Combining simple architectures with large-scale pre-training has led to massive improvements in image classification. For object detection, pre-training and scaling approaches are less well established, especially in the long-tailed and open-vocabulary setting, where training data is relatively scarce. In this paper, we propose a strong recipe for transferring image-text models to open-vocabulary object detection. We use a standard Vision Transformer architecture with minimal modifications, contrastive image-text pre-training, and end-to-end detection fine-tuning. Our analysis of the scaling p"},"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":"2205.06230","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-12T17:20:36Z","cross_cats_sorted":[],"title_canon_sha256":"3434a61164d9733b082f7598190befce1e234d099fb82337b50bef42883d0b8e","abstract_canon_sha256":"0dd54383247bfbd1d4334e396de02656b22d610f60d0326f712a902cf4b19e5f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:41:55.891385Z","signature_b64":"YxBFnDYKSP5d55jZ4ur5/xAt5IkJFtstyzK4gy4fe4IVLxKQKRSilGeItpFxf5sSVo319VxpyrTu5V9ScISFAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"41b1db483bbec6b3eb9a02384d2a3680d3c49346cd76cb7e2190a0278855de2d","last_reissued_at":"2026-07-05T04:41:55.890929Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:41:55.890929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Simple Open-Vocabulary Object Detection with Vision Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexey Dosovitskiy, Alexey Gritsenko, Anurag Arnab, Aravindh Mahendran, Austin Stone, Dirk Weissenborn, Matthias Minderer, Maxim Neumann, Mostafa Dehghani, Neil Houlsby, Thomas Kipf, Xiaohua Zhai, Xiao Wang, Zhuoran Shen","submitted_at":"2022-05-12T17:20:36Z","abstract_excerpt":"Combining simple architectures with large-scale pre-training has led to massive improvements in image classification. For object detection, pre-training and scaling approaches are less well established, especially in the long-tailed and open-vocabulary setting, where training data is relatively scarce. In this paper, we propose a strong recipe for transferring image-text models to open-vocabulary object detection. We use a standard Vision Transformer architecture with minimal modifications, contrastive image-text pre-training, and end-to-end detection fine-tuning. Our analysis of the scaling p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.06230","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2205.06230/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":"2205.06230","created_at":"2026-07-05T04:41:55.890986+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.06230v2","created_at":"2026-07-05T04:41:55.890986+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.06230","created_at":"2026-07-05T04:41:55.890986+00:00"},{"alias_kind":"pith_short_12","alias_value":"IGY5WSB3X3DL","created_at":"2026-07-05T04:41:55.890986+00:00"},{"alias_kind":"pith_short_16","alias_value":"IGY5WSB3X3DLH242","created_at":"2026-07-05T04:41:55.890986+00:00"},{"alias_kind":"pith_short_8","alias_value":"IGY5WSB3","created_at":"2026-07-05T04:41:55.890986+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":14,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26734","citing_title":"Robust Onion: Peeling Open Vocab Object Detectors Under Noise","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09360","citing_title":"ExDet: Open-Domain Open-Vocabulary Detection with Cross-modal Extrapolation and Rectification","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26734","citing_title":"Robust Onion: Peeling Open Vocab Object Detectors Under Noise","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30613","citing_title":"Sequential Planning via Anchored Robotic Keypoints","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28271","citing_title":"LV-OSD: Language-Vision-Complementary Open-Set Object Detection","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2212.12130","citing_title":"Learning to Detect and Segment for Open Vocabulary Object Detection","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19410","citing_title":"Vision Harnessing Agent for Open Ad-hoc Segmentation","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2302.11550","citing_title":"Scaling Robot Learning with Semantically Imagined Experience","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2303.08128","citing_title":"ViperGPT: Visual Inference via Python Execution for Reasoning","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2512.06171","citing_title":"Automated Annotation of Shearographic Measurements Enabling Weakly Supervised Defect Detection","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2409.01652","citing_title":"ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation","ref_index":135,"is_internal_anchor":false},{"citing_arxiv_id":"2603.20554","citing_title":"When Negation Is a Geometry Problem in Vision-Language Models","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2307.05973","citing_title":"VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25358","citing_title":"Benchmarking Layout-Guided Diffusion Models through Unified Semantic-Spatial Evaluation in Closed and Open Settings","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IGY5WSB3X3DLH242AI4E2KRWQD","json":"https://pith.science/pith/IGY5WSB3X3DLH242AI4E2KRWQD.json","graph_json":"https://pith.science/api/pith-number/IGY5WSB3X3DLH242AI4E2KRWQD/graph.json","events_json":"https://pith.science/api/pith-number/IGY5WSB3X3DLH242AI4E2KRWQD/events.json","paper":"https://pith.science/paper/IGY5WSB3"},"agent_actions":{"view_html":"https://pith.science/pith/IGY5WSB3X3DLH242AI4E2KRWQD","download_json":"https://pith.science/pith/IGY5WSB3X3DLH242AI4E2KRWQD.json","view_paper":"https://pith.science/paper/IGY5WSB3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.06230&json=true","fetch_graph":"https://pith.science/api/pith-number/IGY5WSB3X3DLH242AI4E2KRWQD/graph.json","fetch_events":"https://pith.science/api/pith-number/IGY5WSB3X3DLH242AI4E2KRWQD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IGY5WSB3X3DLH242AI4E2KRWQD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IGY5WSB3X3DLH242AI4E2KRWQD/action/storage_attestation","attest_author":"https://pith.science/pith/IGY5WSB3X3DLH242AI4E2KRWQD/action/author_attestation","sign_citation":"https://pith.science/pith/IGY5WSB3X3DLH242AI4E2KRWQD/action/citation_signature","submit_replication":"https://pith.science/pith/IGY5WSB3X3DLH242AI4E2KRWQD/action/replication_record"}},"created_at":"2026-07-05T04:41:55.890986+00:00","updated_at":"2026-07-05T04:41:55.890986+00:00"}