{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LR2WRKMGZHDW6ITOHMFU5WPUNL","short_pith_number":"pith:LR2WRKMG","schema_version":"1.0","canonical_sha256":"5c7568a986c9c76f226e3b0b4ed9f46acca7fa70e8ab9f0131fcdd4403569053","source":{"kind":"arxiv","id":"2210.15138","version":1},"attestation_state":"computed","paper":{"title":"Open-vocabulary Semantic Segmentation with Frozen Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaofan Ma, Weidi Xie, Yanfeng Wang, Ya Zhang, Yuhuan Yang","submitted_at":"2022-10-27T02:57:26Z","abstract_excerpt":"When trained at a sufficient scale, self-supervised learning has exhibited a notable ability to solve a wide range of visual or language understanding tasks. In this paper, we investigate simple, yet effective approaches for adapting the pre-trained foundation models to the downstream task of interest, namely, open-vocabulary semantic segmentation. To this end, we make the following contributions: (i) we introduce Fusioner, with a lightweight, transformer-based fusion module, that pairs the frozen visual representation with language concept through a handful of image segmentation data. As a co"},"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":"2210.15138","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-27T02:57:26Z","cross_cats_sorted":[],"title_canon_sha256":"67d2018b5312f85877e694a1054f417fc35b2d4c1bcfbf8d9b4ec2ebfd430722","abstract_canon_sha256":"d862aadde66a99d0c922d44ae8ed25ce2053d98ff09e60d649aa44533ba252d5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:11:02.583436Z","signature_b64":"QVBaEeLiDLW9j2GRHPItx3fix6vw4a5nNi/K1pE4a+cqMp/HQ2btmBf73mFslVc4KcUyvlj8Awl1YYbgLJOpDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c7568a986c9c76f226e3b0b4ed9f46acca7fa70e8ab9f0131fcdd4403569053","last_reissued_at":"2026-07-05T05:11:02.582996Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:11:02.582996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Open-vocabulary Semantic Segmentation with Frozen Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaofan Ma, Weidi Xie, Yanfeng Wang, Ya Zhang, Yuhuan Yang","submitted_at":"2022-10-27T02:57:26Z","abstract_excerpt":"When trained at a sufficient scale, self-supervised learning has exhibited a notable ability to solve a wide range of visual or language understanding tasks. In this paper, we investigate simple, yet effective approaches for adapting the pre-trained foundation models to the downstream task of interest, namely, open-vocabulary semantic segmentation. To this end, we make the following contributions: (i) we introduce Fusioner, with a lightweight, transformer-based fusion module, that pairs the frozen visual representation with language concept through a handful of image segmentation data. As a co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.15138","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/2210.15138/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":"2210.15138","created_at":"2026-07-05T05:11:02.583052+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.15138v1","created_at":"2026-07-05T05:11:02.583052+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.15138","created_at":"2026-07-05T05:11:02.583052+00:00"},{"alias_kind":"pith_short_12","alias_value":"LR2WRKMGZHDW","created_at":"2026-07-05T05:11:02.583052+00:00"},{"alias_kind":"pith_short_16","alias_value":"LR2WRKMGZHDW6ITO","created_at":"2026-07-05T05:11:02.583052+00:00"},{"alias_kind":"pith_short_8","alias_value":"LR2WRKMG","created_at":"2026-07-05T05:11:02.583052+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.13243","citing_title":"XMask3D: Cross-modal Mask Reasoning for Open Vocabulary 3D Semantic Segmentation","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LR2WRKMGZHDW6ITOHMFU5WPUNL","json":"https://pith.science/pith/LR2WRKMGZHDW6ITOHMFU5WPUNL.json","graph_json":"https://pith.science/api/pith-number/LR2WRKMGZHDW6ITOHMFU5WPUNL/graph.json","events_json":"https://pith.science/api/pith-number/LR2WRKMGZHDW6ITOHMFU5WPUNL/events.json","paper":"https://pith.science/paper/LR2WRKMG"},"agent_actions":{"view_html":"https://pith.science/pith/LR2WRKMGZHDW6ITOHMFU5WPUNL","download_json":"https://pith.science/pith/LR2WRKMGZHDW6ITOHMFU5WPUNL.json","view_paper":"https://pith.science/paper/LR2WRKMG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.15138&json=true","fetch_graph":"https://pith.science/api/pith-number/LR2WRKMGZHDW6ITOHMFU5WPUNL/graph.json","fetch_events":"https://pith.science/api/pith-number/LR2WRKMGZHDW6ITOHMFU5WPUNL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LR2WRKMGZHDW6ITOHMFU5WPUNL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LR2WRKMGZHDW6ITOHMFU5WPUNL/action/storage_attestation","attest_author":"https://pith.science/pith/LR2WRKMGZHDW6ITOHMFU5WPUNL/action/author_attestation","sign_citation":"https://pith.science/pith/LR2WRKMGZHDW6ITOHMFU5WPUNL/action/citation_signature","submit_replication":"https://pith.science/pith/LR2WRKMGZHDW6ITOHMFU5WPUNL/action/replication_record"}},"created_at":"2026-07-05T05:11:02.583052+00:00","updated_at":"2026-07-05T05:11:02.583052+00:00"}