{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:AY5NDLOOQUL3CTQMNI4K3UJPYZ","short_pith_number":"pith:AY5NDLOO","schema_version":"1.0","canonical_sha256":"063ad1adce8517b14e0c6a38add12fc66ee160d0a45a6a1431ab731c91a86528","source":{"kind":"arxiv","id":"2309.12969","version":4},"attestation_state":"computed","paper":{"title":"Detect Everything with Few Examples","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abdeslam Boularias, Xinyu Zhang, Yuhan Liu, Yuting Wang","submitted_at":"2023-09-22T16:07:16Z","abstract_excerpt":"Few-shot object detection aims at detecting novel categories given only a few example images. It is a basic skill for a robot to perform tasks in open environments. Recent methods focus on finetuning strategies, with complicated procedures that prohibit a wider application. In this paper, we introduce DE-ViT, a few-shot object detector without the need for finetuning. DE-ViT's novel architecture is based on a new region-propagation mechanism for localization. The propagated region masks are transformed into bounding boxes through a learnable spatial integral layer. Instead of training prototyp"},"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":"2309.12969","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-22T16:07:16Z","cross_cats_sorted":[],"title_canon_sha256":"a0b51e8109c2ce7f6ec77f8e14d9fa4f5a1abb8f09f2fe5b8a59e37f6762f3bf","abstract_canon_sha256":"f14ff11c5b3aae0159552e2d071cb9a59d591a12d8d0c4ab4281140cef181dc5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:14:53.227557Z","signature_b64":"Ek++kJ6/YtLoOWgqE6J0AruIcZYURGEVVKeRUX6ux/rIPbImp6Vu6vpNv7Kso5UE34wN6M5KcCLre/N5Y8iUCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"063ad1adce8517b14e0c6a38add12fc66ee160d0a45a6a1431ab731c91a86528","last_reissued_at":"2026-07-05T09:14:53.227073Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:14:53.227073Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Detect Everything with Few Examples","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abdeslam Boularias, Xinyu Zhang, Yuhan Liu, Yuting Wang","submitted_at":"2023-09-22T16:07:16Z","abstract_excerpt":"Few-shot object detection aims at detecting novel categories given only a few example images. It is a basic skill for a robot to perform tasks in open environments. Recent methods focus on finetuning strategies, with complicated procedures that prohibit a wider application. In this paper, we introduce DE-ViT, a few-shot object detector without the need for finetuning. DE-ViT's novel architecture is based on a new region-propagation mechanism for localization. The propagated region masks are transformed into bounding boxes through a learnable spatial integral layer. Instead of training prototyp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.12969","kind":"arxiv","version":4},"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/2309.12969/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":"2309.12969","created_at":"2026-07-05T09:14:53.227129+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.12969v4","created_at":"2026-07-05T09:14:53.227129+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.12969","created_at":"2026-07-05T09:14:53.227129+00:00"},{"alias_kind":"pith_short_12","alias_value":"AY5NDLOOQUL3","created_at":"2026-07-05T09:14:53.227129+00:00"},{"alias_kind":"pith_short_16","alias_value":"AY5NDLOOQUL3CTQM","created_at":"2026-07-05T09:14:53.227129+00:00"},{"alias_kind":"pith_short_8","alias_value":"AY5NDLOO","created_at":"2026-07-05T09:14:53.227129+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23069","citing_title":"Rethinking Prototype-based Similarity Learning for Few-Shot Object Detection","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23069","citing_title":"Rethinking Prototype-based Similarity Learning for Few-Shot Object Detection","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11998","citing_title":"The Second Challenge on Cross-Domain Few-Shot Object Detection at NTIRE 2026: Methods and Results","ref_index":125,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AY5NDLOOQUL3CTQMNI4K3UJPYZ","json":"https://pith.science/pith/AY5NDLOOQUL3CTQMNI4K3UJPYZ.json","graph_json":"https://pith.science/api/pith-number/AY5NDLOOQUL3CTQMNI4K3UJPYZ/graph.json","events_json":"https://pith.science/api/pith-number/AY5NDLOOQUL3CTQMNI4K3UJPYZ/events.json","paper":"https://pith.science/paper/AY5NDLOO"},"agent_actions":{"view_html":"https://pith.science/pith/AY5NDLOOQUL3CTQMNI4K3UJPYZ","download_json":"https://pith.science/pith/AY5NDLOOQUL3CTQMNI4K3UJPYZ.json","view_paper":"https://pith.science/paper/AY5NDLOO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.12969&json=true","fetch_graph":"https://pith.science/api/pith-number/AY5NDLOOQUL3CTQMNI4K3UJPYZ/graph.json","fetch_events":"https://pith.science/api/pith-number/AY5NDLOOQUL3CTQMNI4K3UJPYZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AY5NDLOOQUL3CTQMNI4K3UJPYZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AY5NDLOOQUL3CTQMNI4K3UJPYZ/action/storage_attestation","attest_author":"https://pith.science/pith/AY5NDLOOQUL3CTQMNI4K3UJPYZ/action/author_attestation","sign_citation":"https://pith.science/pith/AY5NDLOOQUL3CTQMNI4K3UJPYZ/action/citation_signature","submit_replication":"https://pith.science/pith/AY5NDLOOQUL3CTQMNI4K3UJPYZ/action/replication_record"}},"created_at":"2026-07-05T09:14:53.227129+00:00","updated_at":"2026-07-05T09:14:53.227129+00:00"}