{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IAU2G5XOHBHKVCNUT2JT2R2BDZ","short_pith_number":"pith:IAU2G5XO","schema_version":"1.0","canonical_sha256":"4029a376ee384eaa89b49e933d47411e518575ddae56458f3dfecc1ffdf02e72","source":{"kind":"arxiv","id":"2507.19140","version":1},"attestation_state":"computed","paper":{"title":"Balancing Conservatism and Aggressiveness: Prototype-Affinity Hybrid Network for Few-Shot Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ruilin Yao, Shengwu Xiong, Tianyu Zou, Yi Rong","submitted_at":"2025-07-25T10:22:08Z","abstract_excerpt":"This paper studies the few-shot segmentation (FSS) task, which aims to segment objects belonging to unseen categories in a query image by learning a model on a small number of well-annotated support samples. Our analysis of two mainstream FSS paradigms reveals that the predictions made by prototype learning methods are usually conservative, while those of affinity learning methods tend to be more aggressive. This observation motivates us to balance the conservative and aggressive information captured by these two types of FSS frameworks so as to improve the segmentation performance. To achieve"},"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":"2507.19140","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-25T10:22:08Z","cross_cats_sorted":[],"title_canon_sha256":"5f5c6bf01835d306dff58024ccdf71d9aed34b3156906f0ab776055037304715","abstract_canon_sha256":"e7953589b8427d479359a8de1734d8dc86f19a836ca81760caf3c6c3ace793fb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:43:20.255628Z","signature_b64":"tQFlNdanhdqt5LjovKNnTRGDjN/H6QENyEB1x5Lo8NQXZxE3ShvfoV6RTSgX2sQYR5Di6+dOIbEiHH9v60rwDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4029a376ee384eaa89b49e933d47411e518575ddae56458f3dfecc1ffdf02e72","last_reissued_at":"2026-07-05T11:43:20.255137Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:43:20.255137Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Balancing Conservatism and Aggressiveness: Prototype-Affinity Hybrid Network for Few-Shot Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ruilin Yao, Shengwu Xiong, Tianyu Zou, Yi Rong","submitted_at":"2025-07-25T10:22:08Z","abstract_excerpt":"This paper studies the few-shot segmentation (FSS) task, which aims to segment objects belonging to unseen categories in a query image by learning a model on a small number of well-annotated support samples. Our analysis of two mainstream FSS paradigms reveals that the predictions made by prototype learning methods are usually conservative, while those of affinity learning methods tend to be more aggressive. This observation motivates us to balance the conservative and aggressive information captured by these two types of FSS frameworks so as to improve the segmentation performance. To achieve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.19140","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/2507.19140/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":"2507.19140","created_at":"2026-07-05T11:43:20.255196+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.19140v1","created_at":"2026-07-05T11:43:20.255196+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.19140","created_at":"2026-07-05T11:43:20.255196+00:00"},{"alias_kind":"pith_short_12","alias_value":"IAU2G5XOHBHK","created_at":"2026-07-05T11:43:20.255196+00:00"},{"alias_kind":"pith_short_16","alias_value":"IAU2G5XOHBHKVCNU","created_at":"2026-07-05T11:43:20.255196+00:00"},{"alias_kind":"pith_short_8","alias_value":"IAU2G5XO","created_at":"2026-07-05T11:43:20.255196+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/IAU2G5XOHBHKVCNUT2JT2R2BDZ","json":"https://pith.science/pith/IAU2G5XOHBHKVCNUT2JT2R2BDZ.json","graph_json":"https://pith.science/api/pith-number/IAU2G5XOHBHKVCNUT2JT2R2BDZ/graph.json","events_json":"https://pith.science/api/pith-number/IAU2G5XOHBHKVCNUT2JT2R2BDZ/events.json","paper":"https://pith.science/paper/IAU2G5XO"},"agent_actions":{"view_html":"https://pith.science/pith/IAU2G5XOHBHKVCNUT2JT2R2BDZ","download_json":"https://pith.science/pith/IAU2G5XOHBHKVCNUT2JT2R2BDZ.json","view_paper":"https://pith.science/paper/IAU2G5XO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.19140&json=true","fetch_graph":"https://pith.science/api/pith-number/IAU2G5XOHBHKVCNUT2JT2R2BDZ/graph.json","fetch_events":"https://pith.science/api/pith-number/IAU2G5XOHBHKVCNUT2JT2R2BDZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IAU2G5XOHBHKVCNUT2JT2R2BDZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IAU2G5XOHBHKVCNUT2JT2R2BDZ/action/storage_attestation","attest_author":"https://pith.science/pith/IAU2G5XOHBHKVCNUT2JT2R2BDZ/action/author_attestation","sign_citation":"https://pith.science/pith/IAU2G5XOHBHKVCNUT2JT2R2BDZ/action/citation_signature","submit_replication":"https://pith.science/pith/IAU2G5XOHBHKVCNUT2JT2R2BDZ/action/replication_record"}},"created_at":"2026-07-05T11:43:20.255196+00:00","updated_at":"2026-07-05T11:43:20.255196+00:00"}