{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:WEPYMMNFBUAYIM7UX3FRIOWKBY","short_pith_number":"pith:WEPYMMNF","schema_version":"1.0","canonical_sha256":"b11f8631a50d018433f4becb143aca0e121812dfb82a760c37bd9c7b39d257f1","source":{"kind":"arxiv","id":"2103.16549","version":1},"attestation_state":"computed","paper":{"title":"Deep 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":"2021-03-30T17:56:32Z","abstract_excerpt":"Few-shot segmentation is a challenging task, requiring the extraction of a generalizable representation from only a few annotated samples, in order to segment novel query images. A common approach is to model each class with a single prototype. While conceptually simple, these methods suffer when the target appearance distribution is multi-modal or not linearly separable in feature space. To tackle this issue, we propose a few-shot learner formulation based on Gaussian process (GP) regression. Through the expressivity of the GP, our approach is capable of modeling complex appearance distributi"},"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":"2103.16549","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-03-30T17:56:32Z","cross_cats_sorted":[],"title_canon_sha256":"2f08cf3216cd3e30ff7b5a79c6b06097fe922d55f7f8fc34318a67314e18298a","abstract_canon_sha256":"776d60c28a24e122fd930c6ccb6bc2bb5666c18568fbd5cd6d70baf7415a0b02"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:27:53.335408Z","signature_b64":"J956qypkdE298goh5T4TI30w8NMSWedVyOytp7AqZeU7RYnZaEBOCRBO4+lV2UETeHS1N1OVgFKqxuYcYv6oCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b11f8631a50d018433f4becb143aca0e121812dfb82a760c37bd9c7b39d257f1","last_reissued_at":"2026-07-05T02:27:53.334976Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:27:53.334976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep 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":"2021-03-30T17:56:32Z","abstract_excerpt":"Few-shot segmentation is a challenging task, requiring the extraction of a generalizable representation from only a few annotated samples, in order to segment novel query images. A common approach is to model each class with a single prototype. While conceptually simple, these methods suffer when the target appearance distribution is multi-modal or not linearly separable in feature space. To tackle this issue, we propose a few-shot learner formulation based on Gaussian process (GP) regression. Through the expressivity of the GP, our approach is capable of modeling complex appearance distributi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.16549","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/2103.16549/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":"2103.16549","created_at":"2026-07-05T02:27:53.335041+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.16549v1","created_at":"2026-07-05T02:27:53.335041+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.16549","created_at":"2026-07-05T02:27:53.335041+00:00"},{"alias_kind":"pith_short_12","alias_value":"WEPYMMNFBUAY","created_at":"2026-07-05T02:27:53.335041+00:00"},{"alias_kind":"pith_short_16","alias_value":"WEPYMMNFBUAYIM7U","created_at":"2026-07-05T02:27:53.335041+00:00"},{"alias_kind":"pith_short_8","alias_value":"WEPYMMNF","created_at":"2026-07-05T02:27:53.335041+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/WEPYMMNFBUAYIM7UX3FRIOWKBY","json":"https://pith.science/pith/WEPYMMNFBUAYIM7UX3FRIOWKBY.json","graph_json":"https://pith.science/api/pith-number/WEPYMMNFBUAYIM7UX3FRIOWKBY/graph.json","events_json":"https://pith.science/api/pith-number/WEPYMMNFBUAYIM7UX3FRIOWKBY/events.json","paper":"https://pith.science/paper/WEPYMMNF"},"agent_actions":{"view_html":"https://pith.science/pith/WEPYMMNFBUAYIM7UX3FRIOWKBY","download_json":"https://pith.science/pith/WEPYMMNFBUAYIM7UX3FRIOWKBY.json","view_paper":"https://pith.science/paper/WEPYMMNF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.16549&json=true","fetch_graph":"https://pith.science/api/pith-number/WEPYMMNFBUAYIM7UX3FRIOWKBY/graph.json","fetch_events":"https://pith.science/api/pith-number/WEPYMMNFBUAYIM7UX3FRIOWKBY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WEPYMMNFBUAYIM7UX3FRIOWKBY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WEPYMMNFBUAYIM7UX3FRIOWKBY/action/storage_attestation","attest_author":"https://pith.science/pith/WEPYMMNFBUAYIM7UX3FRIOWKBY/action/author_attestation","sign_citation":"https://pith.science/pith/WEPYMMNFBUAYIM7UX3FRIOWKBY/action/citation_signature","submit_replication":"https://pith.science/pith/WEPYMMNFBUAYIM7UX3FRIOWKBY/action/replication_record"}},"created_at":"2026-07-05T02:27:53.335041+00:00","updated_at":"2026-07-05T02:27:53.335041+00:00"}