{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GI37BHOWLMVM5LQHXRSUFTD62B","short_pith_number":"pith:GI37BHOW","schema_version":"1.0","canonical_sha256":"3237f09dd65b2aceae07bc6542cc7ed05520145093df33c987ace976d5aa3f81","source":{"kind":"arxiv","id":"2301.13411","version":1},"attestation_state":"computed","paper":{"title":"Few-Shot Object Detection via Variational Feature Aggregation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gui-Song Xia, Jiaming Han, Jian Ding, Ke Yan, Yuqiang Ren","submitted_at":"2023-01-31T04:58:21Z","abstract_excerpt":"As few-shot object detectors are often trained with abundant base samples and fine-tuned on few-shot novel examples,the learned models are usually biased to base classes and sensitive to the variance of novel examples. To address this issue, we propose a meta-learning framework with two novel feature aggregation schemes. More precisely, we first present a Class-Agnostic Aggregation (CAA) method, where the query and support features can be aggregated regardless of their categories. The interactions between different classes encourage class-agnostic representations and reduce confusion between b"},"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":"2301.13411","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-01-31T04:58:21Z","cross_cats_sorted":[],"title_canon_sha256":"4cb537f2e8d36aa6cda7bb906dab146065ddf999e54f12bb0d34f9ed2c7782aa","abstract_canon_sha256":"2e7a02481ab07a414bf46fbf512d2166b071181cbd82322be62e6c3387ed6637"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:37:14.462772Z","signature_b64":"kR1R4fq/HB6qfjzk+TyXw4Ksk7HH/vBST2C95u1s7z4QbNCPcQZCMNZCWpqT0PD2WUYzXKO+I2R1w5SGgS9jBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3237f09dd65b2aceae07bc6542cc7ed05520145093df33c987ace976d5aa3f81","last_reissued_at":"2026-07-05T05:37:14.462401Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:37:14.462401Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Few-Shot Object Detection via Variational Feature Aggregation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gui-Song Xia, Jiaming Han, Jian Ding, Ke Yan, Yuqiang Ren","submitted_at":"2023-01-31T04:58:21Z","abstract_excerpt":"As few-shot object detectors are often trained with abundant base samples and fine-tuned on few-shot novel examples,the learned models are usually biased to base classes and sensitive to the variance of novel examples. To address this issue, we propose a meta-learning framework with two novel feature aggregation schemes. More precisely, we first present a Class-Agnostic Aggregation (CAA) method, where the query and support features can be aggregated regardless of their categories. The interactions between different classes encourage class-agnostic representations and reduce confusion between b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.13411","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/2301.13411/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":"2301.13411","created_at":"2026-07-05T05:37:14.462458+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.13411v1","created_at":"2026-07-05T05:37:14.462458+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.13411","created_at":"2026-07-05T05:37:14.462458+00:00"},{"alias_kind":"pith_short_12","alias_value":"GI37BHOWLMVM","created_at":"2026-07-05T05:37:14.462458+00:00"},{"alias_kind":"pith_short_16","alias_value":"GI37BHOWLMVM5LQH","created_at":"2026-07-05T05:37:14.462458+00:00"},{"alias_kind":"pith_short_8","alias_value":"GI37BHOW","created_at":"2026-07-05T05:37:14.462458+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.18326","citing_title":"Enhancing Few-Shot Classification of Benchmark and Disaster Imagery with ABHFA-Net","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GI37BHOWLMVM5LQHXRSUFTD62B","json":"https://pith.science/pith/GI37BHOWLMVM5LQHXRSUFTD62B.json","graph_json":"https://pith.science/api/pith-number/GI37BHOWLMVM5LQHXRSUFTD62B/graph.json","events_json":"https://pith.science/api/pith-number/GI37BHOWLMVM5LQHXRSUFTD62B/events.json","paper":"https://pith.science/paper/GI37BHOW"},"agent_actions":{"view_html":"https://pith.science/pith/GI37BHOWLMVM5LQHXRSUFTD62B","download_json":"https://pith.science/pith/GI37BHOWLMVM5LQHXRSUFTD62B.json","view_paper":"https://pith.science/paper/GI37BHOW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.13411&json=true","fetch_graph":"https://pith.science/api/pith-number/GI37BHOWLMVM5LQHXRSUFTD62B/graph.json","fetch_events":"https://pith.science/api/pith-number/GI37BHOWLMVM5LQHXRSUFTD62B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GI37BHOWLMVM5LQHXRSUFTD62B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GI37BHOWLMVM5LQHXRSUFTD62B/action/storage_attestation","attest_author":"https://pith.science/pith/GI37BHOWLMVM5LQHXRSUFTD62B/action/author_attestation","sign_citation":"https://pith.science/pith/GI37BHOWLMVM5LQHXRSUFTD62B/action/citation_signature","submit_replication":"https://pith.science/pith/GI37BHOWLMVM5LQHXRSUFTD62B/action/replication_record"}},"created_at":"2026-07-05T05:37:14.462458+00:00","updated_at":"2026-07-05T05:37:14.462458+00:00"}