{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RMKFDEEZIQ3Y3SZZL6U4ZQ6PVP","short_pith_number":"pith:RMKFDEEZ","schema_version":"1.0","canonical_sha256":"8b1451909944378dcb395fa9ccc3cfabc73cba2ad2a79e24dc312efab86e49d8","source":{"kind":"arxiv","id":"2407.02075","version":4},"attestation_state":"computed","paper":{"title":"Label Anything: Multi-Class Few-Shot Semantic Segmentation with Visual Prompts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Emanuele Colonna, Gennaro Vessio, Giovanna Castellano, Giuseppe Fiameni, Nicola Fanelli, Pasquale De Marinis, Raffaele Scaringi","submitted_at":"2024-07-02T09:08:06Z","abstract_excerpt":"Few-shot semantic segmentation aims to segment objects from previously unseen classes using only a limited number of labeled examples. In this paper, we introduce Label Anything, a novel transformer-based architecture designed for multi-prompt, multi-way few-shot semantic segmentation. Our approach leverages diverse visual prompts -- points, bounding boxes, and masks -- to create a highly flexible and generalizable framework that significantly reduces annotation burden while maintaining high accuracy. Label Anything makes three key contributions: ($\\textit{i}$) we introduce a new task formulat"},"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":"2407.02075","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-02T09:08:06Z","cross_cats_sorted":[],"title_canon_sha256":"0f561fc45799b1005956aca2ba1798626a6ea6af9ce42454df324fdbd10fb05b","abstract_canon_sha256":"6559bd49045a4dc908b51e6389a1443af2a21f221263e2abef729f7091c49875"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:56:48.885027Z","signature_b64":"LFnhjLgucVo02NZgJdsGzexsXjY63ILDDSx2o33Kbb36rHNXnaDJNEl4nnp1yPsny1CUx6AGAXqRhOTYrUGSAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b1451909944378dcb395fa9ccc3cfabc73cba2ad2a79e24dc312efab86e49d8","last_reissued_at":"2026-07-05T11:56:48.884524Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:56:48.884524Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Label Anything: Multi-Class Few-Shot Semantic Segmentation with Visual Prompts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Emanuele Colonna, Gennaro Vessio, Giovanna Castellano, Giuseppe Fiameni, Nicola Fanelli, Pasquale De Marinis, Raffaele Scaringi","submitted_at":"2024-07-02T09:08:06Z","abstract_excerpt":"Few-shot semantic segmentation aims to segment objects from previously unseen classes using only a limited number of labeled examples. In this paper, we introduce Label Anything, a novel transformer-based architecture designed for multi-prompt, multi-way few-shot semantic segmentation. Our approach leverages diverse visual prompts -- points, bounding boxes, and masks -- to create a highly flexible and generalizable framework that significantly reduces annotation burden while maintaining high accuracy. Label Anything makes three key contributions: ($\\textit{i}$) we introduce a new task formulat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.02075","kind":"arxiv","version":4},"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/2407.02075/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":"2407.02075","created_at":"2026-07-05T11:56:48.884582+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.02075v4","created_at":"2026-07-05T11:56:48.884582+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.02075","created_at":"2026-07-05T11:56:48.884582+00:00"},{"alias_kind":"pith_short_12","alias_value":"RMKFDEEZIQ3Y","created_at":"2026-07-05T11:56:48.884582+00:00"},{"alias_kind":"pith_short_16","alias_value":"RMKFDEEZIQ3Y3SZZ","created_at":"2026-07-05T11:56:48.884582+00:00"},{"alias_kind":"pith_short_8","alias_value":"RMKFDEEZ","created_at":"2026-07-05T11:56:48.884582+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.09562","citing_title":"Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges","ref_index":45,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RMKFDEEZIQ3Y3SZZL6U4ZQ6PVP","json":"https://pith.science/pith/RMKFDEEZIQ3Y3SZZL6U4ZQ6PVP.json","graph_json":"https://pith.science/api/pith-number/RMKFDEEZIQ3Y3SZZL6U4ZQ6PVP/graph.json","events_json":"https://pith.science/api/pith-number/RMKFDEEZIQ3Y3SZZL6U4ZQ6PVP/events.json","paper":"https://pith.science/paper/RMKFDEEZ"},"agent_actions":{"view_html":"https://pith.science/pith/RMKFDEEZIQ3Y3SZZL6U4ZQ6PVP","download_json":"https://pith.science/pith/RMKFDEEZIQ3Y3SZZL6U4ZQ6PVP.json","view_paper":"https://pith.science/paper/RMKFDEEZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.02075&json=true","fetch_graph":"https://pith.science/api/pith-number/RMKFDEEZIQ3Y3SZZL6U4ZQ6PVP/graph.json","fetch_events":"https://pith.science/api/pith-number/RMKFDEEZIQ3Y3SZZL6U4ZQ6PVP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RMKFDEEZIQ3Y3SZZL6U4ZQ6PVP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RMKFDEEZIQ3Y3SZZL6U4ZQ6PVP/action/storage_attestation","attest_author":"https://pith.science/pith/RMKFDEEZIQ3Y3SZZL6U4ZQ6PVP/action/author_attestation","sign_citation":"https://pith.science/pith/RMKFDEEZIQ3Y3SZZL6U4ZQ6PVP/action/citation_signature","submit_replication":"https://pith.science/pith/RMKFDEEZIQ3Y3SZZL6U4ZQ6PVP/action/replication_record"}},"created_at":"2026-07-05T11:56:48.884582+00:00","updated_at":"2026-07-05T11:56:48.884582+00:00"}