{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ENPMELBYKRZ73KBITWL3GRYYQO","short_pith_number":"pith:ENPMELBY","schema_version":"1.0","canonical_sha256":"235ec22c385473fda8289d97b347188393c6b4388f9b485d30460fbb160317a4","source":{"kind":"arxiv","id":"2208.00306","version":1},"attestation_state":"computed","paper":{"title":"Doubly Deformable Aggregation of Covariance Matrices for Few-shot Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haopeng Li, Xiao Xiang Zhu, Zhitong Xiong","submitted_at":"2022-07-30T20:41:38Z","abstract_excerpt":"Training semantic segmentation models with few annotated samples has great potential in various real-world applications. For the few-shot segmentation task, the main challenge is how to accurately measure the semantic correspondence between the support and query samples with limited training data. To address this problem, we propose to aggregate the learnable covariance matrices with a deformable 4D Transformer to effectively predict the segmentation map. Specifically, in this work, we first devise a novel hard example mining mechanism to learn covariance kernels for the Gaussian process. The "},"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":"2208.00306","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-07-30T20:41:38Z","cross_cats_sorted":[],"title_canon_sha256":"bef480f90ed10b433d18277dec808ecd8fc5e6cfc911d769f4818fe4767ebeec","abstract_canon_sha256":"a60c112e7f9aa32a3536e6f0baa3967aa3df89a2b1247fa4453d05929f9da1b8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:44:49.981615Z","signature_b64":"S85q5OFhQi2W8K4m16O5tPXHTy3Em0cxIYBxHZDRG/0W8qfZm5eK1B7MkhX0KqmBBJwazDKw1l9KxgsxT59FAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"235ec22c385473fda8289d97b347188393c6b4388f9b485d30460fbb160317a4","last_reissued_at":"2026-07-05T04:44:49.981118Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:44:49.981118Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Doubly Deformable Aggregation of Covariance Matrices for Few-shot Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haopeng Li, Xiao Xiang Zhu, Zhitong Xiong","submitted_at":"2022-07-30T20:41:38Z","abstract_excerpt":"Training semantic segmentation models with few annotated samples has great potential in various real-world applications. For the few-shot segmentation task, the main challenge is how to accurately measure the semantic correspondence between the support and query samples with limited training data. To address this problem, we propose to aggregate the learnable covariance matrices with a deformable 4D Transformer to effectively predict the segmentation map. Specifically, in this work, we first devise a novel hard example mining mechanism to learn covariance kernels for the Gaussian process. The "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.00306","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/2208.00306/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":"2208.00306","created_at":"2026-07-05T04:44:49.981173+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.00306v1","created_at":"2026-07-05T04:44:49.981173+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.00306","created_at":"2026-07-05T04:44:49.981173+00:00"},{"alias_kind":"pith_short_12","alias_value":"ENPMELBYKRZ7","created_at":"2026-07-05T04:44:49.981173+00:00"},{"alias_kind":"pith_short_16","alias_value":"ENPMELBYKRZ73KBI","created_at":"2026-07-05T04:44:49.981173+00:00"},{"alias_kind":"pith_short_8","alias_value":"ENPMELBY","created_at":"2026-07-05T04:44:49.981173+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/ENPMELBYKRZ73KBITWL3GRYYQO","json":"https://pith.science/pith/ENPMELBYKRZ73KBITWL3GRYYQO.json","graph_json":"https://pith.science/api/pith-number/ENPMELBYKRZ73KBITWL3GRYYQO/graph.json","events_json":"https://pith.science/api/pith-number/ENPMELBYKRZ73KBITWL3GRYYQO/events.json","paper":"https://pith.science/paper/ENPMELBY"},"agent_actions":{"view_html":"https://pith.science/pith/ENPMELBYKRZ73KBITWL3GRYYQO","download_json":"https://pith.science/pith/ENPMELBYKRZ73KBITWL3GRYYQO.json","view_paper":"https://pith.science/paper/ENPMELBY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.00306&json=true","fetch_graph":"https://pith.science/api/pith-number/ENPMELBYKRZ73KBITWL3GRYYQO/graph.json","fetch_events":"https://pith.science/api/pith-number/ENPMELBYKRZ73KBITWL3GRYYQO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ENPMELBYKRZ73KBITWL3GRYYQO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ENPMELBYKRZ73KBITWL3GRYYQO/action/storage_attestation","attest_author":"https://pith.science/pith/ENPMELBYKRZ73KBITWL3GRYYQO/action/author_attestation","sign_citation":"https://pith.science/pith/ENPMELBYKRZ73KBITWL3GRYYQO/action/citation_signature","submit_replication":"https://pith.science/pith/ENPMELBYKRZ73KBITWL3GRYYQO/action/replication_record"}},"created_at":"2026-07-05T04:44:49.981173+00:00","updated_at":"2026-07-05T04:44:49.981173+00:00"}