{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:2VMCSXAOXKOWQYNJTTP2DCE6AB","short_pith_number":"pith:2VMCSXAO","schema_version":"1.0","canonical_sha256":"d558295c0eba9d6861a99cdfa1889e005b4603e0fd1b098a80c0d74f0e6719ea","source":{"kind":"arxiv","id":"2110.03674","version":2},"attestation_state":"computed","paper":{"title":"Dense Gaussian Processes for Few-Shot Segmentation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fahad Shahbaz Khan, Joakim Johnander, Johan Edstedt, Martin Danelljan, Michael Felsberg","submitted_at":"2021-10-07T17:57:54Z","abstract_excerpt":"Few-shot segmentation is a challenging dense prediction task, which entails segmenting a novel query image given only a small annotated support set. The key problem is thus to design a method that aggregates detailed information from the support set, while being robust to large variations in appearance and context. To this end, we propose a few-shot segmentation method based on dense Gaussian process (GP) regression. Given the support set, our dense GP learns the mapping from local deep image features to mask values, capable of capturing complex appearance distributions. Furthermore, it provid"},"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":"2110.03674","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-07T17:57:54Z","cross_cats_sorted":[],"title_canon_sha256":"d7d66d8c9f342d1948b4490d8e2d24565f4393030c6ae01cc96472ba03697971","abstract_canon_sha256":"02e4524ec989bf431755e7bb11e6c7340ba32fb5b56a59f9fd4aba89ba01c434"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:53:25.469186Z","signature_b64":"PCpkM4RatHggzjX0hlTO+fk0tXhBVY0D6DCYjOe4bxxDcgOPNoXdOFvdrXSSbl8F1K7U8BxUW6bZlHOSm5ZvCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d558295c0eba9d6861a99cdfa1889e005b4603e0fd1b098a80c0d74f0e6719ea","last_reissued_at":"2026-07-05T04:53:25.468676Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:53:25.468676Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dense Gaussian Processes for Few-Shot Segmentation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fahad Shahbaz Khan, Joakim Johnander, Johan Edstedt, Martin Danelljan, Michael Felsberg","submitted_at":"2021-10-07T17:57:54Z","abstract_excerpt":"Few-shot segmentation is a challenging dense prediction task, which entails segmenting a novel query image given only a small annotated support set. The key problem is thus to design a method that aggregates detailed information from the support set, while being robust to large variations in appearance and context. To this end, we propose a few-shot segmentation method based on dense Gaussian process (GP) regression. Given the support set, our dense GP learns the mapping from local deep image features to mask values, capable of capturing complex appearance distributions. Furthermore, it provid"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.03674","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/2110.03674/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":"2110.03674","created_at":"2026-07-05T04:53:25.468738+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.03674v2","created_at":"2026-07-05T04:53:25.468738+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.03674","created_at":"2026-07-05T04:53:25.468738+00:00"},{"alias_kind":"pith_short_12","alias_value":"2VMCSXAOXKOW","created_at":"2026-07-05T04:53:25.468738+00:00"},{"alias_kind":"pith_short_16","alias_value":"2VMCSXAOXKOWQYNJ","created_at":"2026-07-05T04:53:25.468738+00:00"},{"alias_kind":"pith_short_8","alias_value":"2VMCSXAO","created_at":"2026-07-05T04:53:25.468738+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/2VMCSXAOXKOWQYNJTTP2DCE6AB","json":"https://pith.science/pith/2VMCSXAOXKOWQYNJTTP2DCE6AB.json","graph_json":"https://pith.science/api/pith-number/2VMCSXAOXKOWQYNJTTP2DCE6AB/graph.json","events_json":"https://pith.science/api/pith-number/2VMCSXAOXKOWQYNJTTP2DCE6AB/events.json","paper":"https://pith.science/paper/2VMCSXAO"},"agent_actions":{"view_html":"https://pith.science/pith/2VMCSXAOXKOWQYNJTTP2DCE6AB","download_json":"https://pith.science/pith/2VMCSXAOXKOWQYNJTTP2DCE6AB.json","view_paper":"https://pith.science/paper/2VMCSXAO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.03674&json=true","fetch_graph":"https://pith.science/api/pith-number/2VMCSXAOXKOWQYNJTTP2DCE6AB/graph.json","fetch_events":"https://pith.science/api/pith-number/2VMCSXAOXKOWQYNJTTP2DCE6AB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2VMCSXAOXKOWQYNJTTP2DCE6AB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2VMCSXAOXKOWQYNJTTP2DCE6AB/action/storage_attestation","attest_author":"https://pith.science/pith/2VMCSXAOXKOWQYNJTTP2DCE6AB/action/author_attestation","sign_citation":"https://pith.science/pith/2VMCSXAOXKOWQYNJTTP2DCE6AB/action/citation_signature","submit_replication":"https://pith.science/pith/2VMCSXAOXKOWQYNJTTP2DCE6AB/action/replication_record"}},"created_at":"2026-07-05T04:53:25.468738+00:00","updated_at":"2026-07-05T04:53:25.468738+00:00"}