{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:6OGDQVNNICGF2T3XK5SA7QAKDZ","short_pith_number":"pith:6OGDQVNN","schema_version":"1.0","canonical_sha256":"f38c3855ad408c5d4f7757640fc00a1e5827b741a4cf03411a079b5d048f3307","source":{"kind":"arxiv","id":"2204.09903","version":2},"attestation_state":"computed","paper":{"title":"Beyond the Prototype: Divide-and-conquer Proxies for Few-shot Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Binfei Tu, Chunbo Lang, Gong Cheng, Junwei Han","submitted_at":"2022-04-21T06:21:14Z","abstract_excerpt":"Few-shot segmentation, which aims to segment unseen-class objects given only a handful of densely labeled samples, has received widespread attention from the community. Existing approaches typically follow the prototype learning paradigm to perform meta-inference, which fails to fully exploit the underlying information from support image-mask pairs, resulting in various segmentation failures, e.g., incomplete objects, ambiguous boundaries, and distractor activation. To this end, we propose a simple yet versatile framework in the spirit of divide-and-conquer. Specifically, a novel self-reasonin"},"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":"2204.09903","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-21T06:21:14Z","cross_cats_sorted":[],"title_canon_sha256":"62adb22242f203a2a0d3a929b153b4848137909975c672bf96a75ccd2be2693f","abstract_canon_sha256":"c7d3ca5c5b6d87a5400a5b4ccaf4664b678b880113c1d801bf43a471e8fa9637"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:27:12.941940Z","signature_b64":"OGIrm9CcA/boEHj6Db93JfP85JkB34iXuT+c5R7OqFlMUeRMiYixRDRE2aBhL+4qqr7UIfpNTuKUYkTPWKm3Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f38c3855ad408c5d4f7757640fc00a1e5827b741a4cf03411a079b5d048f3307","last_reissued_at":"2026-07-05T04:27:12.941486Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:27:12.941486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond the Prototype: Divide-and-conquer Proxies for Few-shot Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Binfei Tu, Chunbo Lang, Gong Cheng, Junwei Han","submitted_at":"2022-04-21T06:21:14Z","abstract_excerpt":"Few-shot segmentation, which aims to segment unseen-class objects given only a handful of densely labeled samples, has received widespread attention from the community. Existing approaches typically follow the prototype learning paradigm to perform meta-inference, which fails to fully exploit the underlying information from support image-mask pairs, resulting in various segmentation failures, e.g., incomplete objects, ambiguous boundaries, and distractor activation. To this end, we propose a simple yet versatile framework in the spirit of divide-and-conquer. Specifically, a novel self-reasonin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.09903","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/2204.09903/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":"2204.09903","created_at":"2026-07-05T04:27:12.941542+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.09903v2","created_at":"2026-07-05T04:27:12.941542+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.09903","created_at":"2026-07-05T04:27:12.941542+00:00"},{"alias_kind":"pith_short_12","alias_value":"6OGDQVNNICGF","created_at":"2026-07-05T04:27:12.941542+00:00"},{"alias_kind":"pith_short_16","alias_value":"6OGDQVNNICGF2T3X","created_at":"2026-07-05T04:27:12.941542+00:00"},{"alias_kind":"pith_short_8","alias_value":"6OGDQVNN","created_at":"2026-07-05T04:27:12.941542+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.19140","citing_title":"Balancing Conservatism and Aggressiveness: Prototype-Affinity Hybrid Network for Few-Shot Segmentation","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6OGDQVNNICGF2T3XK5SA7QAKDZ","json":"https://pith.science/pith/6OGDQVNNICGF2T3XK5SA7QAKDZ.json","graph_json":"https://pith.science/api/pith-number/6OGDQVNNICGF2T3XK5SA7QAKDZ/graph.json","events_json":"https://pith.science/api/pith-number/6OGDQVNNICGF2T3XK5SA7QAKDZ/events.json","paper":"https://pith.science/paper/6OGDQVNN"},"agent_actions":{"view_html":"https://pith.science/pith/6OGDQVNNICGF2T3XK5SA7QAKDZ","download_json":"https://pith.science/pith/6OGDQVNNICGF2T3XK5SA7QAKDZ.json","view_paper":"https://pith.science/paper/6OGDQVNN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.09903&json=true","fetch_graph":"https://pith.science/api/pith-number/6OGDQVNNICGF2T3XK5SA7QAKDZ/graph.json","fetch_events":"https://pith.science/api/pith-number/6OGDQVNNICGF2T3XK5SA7QAKDZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6OGDQVNNICGF2T3XK5SA7QAKDZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6OGDQVNNICGF2T3XK5SA7QAKDZ/action/storage_attestation","attest_author":"https://pith.science/pith/6OGDQVNNICGF2T3XK5SA7QAKDZ/action/author_attestation","sign_citation":"https://pith.science/pith/6OGDQVNNICGF2T3XK5SA7QAKDZ/action/citation_signature","submit_replication":"https://pith.science/pith/6OGDQVNNICGF2T3XK5SA7QAKDZ/action/replication_record"}},"created_at":"2026-07-05T04:27:12.941542+00:00","updated_at":"2026-07-05T04:27:12.941542+00:00"}