{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KK3K3NN4LFPFVEWORNBNYI36WU","short_pith_number":"pith:KK3K3NN4","schema_version":"1.0","canonical_sha256":"52b6adb5bc595e5a92ce8b42dc237eb50a1714c2cc5acfa535c4b9742a2c9445","source":{"kind":"arxiv","id":"2312.06474","version":1},"attestation_state":"computed","paper":{"title":"Relevant Intrinsic Feature Enhancement Network for Few-Shot Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jie Qin, Siyang Sun, Xiaoyi Bao, Xingang Wang, Yun Zheng","submitted_at":"2023-12-11T16:02:57Z","abstract_excerpt":"For few-shot semantic segmentation, the primary task is to extract class-specific intrinsic information from limited labeled data. However, the semantic ambiguity and inter-class similarity of previous methods limit the accuracy of pixel-level foreground-background classification. To alleviate these issues, we propose the Relevant Intrinsic Feature Enhancement Network (RiFeNet). To improve the semantic consistency of foreground instances, we propose an unlabeled branch as an efficient data utilization method, which teaches the model how to extract intrinsic features robust to intra-class diffe"},"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":"2312.06474","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-11T16:02:57Z","cross_cats_sorted":[],"title_canon_sha256":"710d3aa5564b324db8c7110d7ac756e787e4f05346c82c4ab8d90ff2588fbbc8","abstract_canon_sha256":"6a464c315b8e1c2218fac56ab99d3cf3e022c593cd8f3c5bfe9fd128844ca1d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:22:45.547487Z","signature_b64":"krmdWhAGYtCJfaG6h08nNF2g1VJJ91oWNfOP3FHHJ5aS5UmnW20k9o6eZK+7S3tPRPBeiGayk+4WNGFnpp0fAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52b6adb5bc595e5a92ce8b42dc237eb50a1714c2cc5acfa535c4b9742a2c9445","last_reissued_at":"2026-07-05T07:22:45.546967Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:22:45.546967Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Relevant Intrinsic Feature Enhancement Network for Few-Shot Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jie Qin, Siyang Sun, Xiaoyi Bao, Xingang Wang, Yun Zheng","submitted_at":"2023-12-11T16:02:57Z","abstract_excerpt":"For few-shot semantic segmentation, the primary task is to extract class-specific intrinsic information from limited labeled data. However, the semantic ambiguity and inter-class similarity of previous methods limit the accuracy of pixel-level foreground-background classification. To alleviate these issues, we propose the Relevant Intrinsic Feature Enhancement Network (RiFeNet). To improve the semantic consistency of foreground instances, we propose an unlabeled branch as an efficient data utilization method, which teaches the model how to extract intrinsic features robust to intra-class diffe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.06474","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/2312.06474/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":"2312.06474","created_at":"2026-07-05T07:22:45.547030+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.06474v1","created_at":"2026-07-05T07:22:45.547030+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.06474","created_at":"2026-07-05T07:22:45.547030+00:00"},{"alias_kind":"pith_short_12","alias_value":"KK3K3NN4LFPF","created_at":"2026-07-05T07:22:45.547030+00:00"},{"alias_kind":"pith_short_16","alias_value":"KK3K3NN4LFPFVEWO","created_at":"2026-07-05T07:22:45.547030+00:00"},{"alias_kind":"pith_short_8","alias_value":"KK3K3NN4","created_at":"2026-07-05T07:22:45.547030+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.12685","citing_title":"Enhanced Sign Language Translation between American Sign Language (ASL) and Indian Sign Language (ISL) Using LLMs","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KK3K3NN4LFPFVEWORNBNYI36WU","json":"https://pith.science/pith/KK3K3NN4LFPFVEWORNBNYI36WU.json","graph_json":"https://pith.science/api/pith-number/KK3K3NN4LFPFVEWORNBNYI36WU/graph.json","events_json":"https://pith.science/api/pith-number/KK3K3NN4LFPFVEWORNBNYI36WU/events.json","paper":"https://pith.science/paper/KK3K3NN4"},"agent_actions":{"view_html":"https://pith.science/pith/KK3K3NN4LFPFVEWORNBNYI36WU","download_json":"https://pith.science/pith/KK3K3NN4LFPFVEWORNBNYI36WU.json","view_paper":"https://pith.science/paper/KK3K3NN4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.06474&json=true","fetch_graph":"https://pith.science/api/pith-number/KK3K3NN4LFPFVEWORNBNYI36WU/graph.json","fetch_events":"https://pith.science/api/pith-number/KK3K3NN4LFPFVEWORNBNYI36WU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KK3K3NN4LFPFVEWORNBNYI36WU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KK3K3NN4LFPFVEWORNBNYI36WU/action/storage_attestation","attest_author":"https://pith.science/pith/KK3K3NN4LFPFVEWORNBNYI36WU/action/author_attestation","sign_citation":"https://pith.science/pith/KK3K3NN4LFPFVEWORNBNYI36WU/action/citation_signature","submit_replication":"https://pith.science/pith/KK3K3NN4LFPFVEWORNBNYI36WU/action/replication_record"}},"created_at":"2026-07-05T07:22:45.547030+00:00","updated_at":"2026-07-05T07:22:45.547030+00:00"}