{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:C5WQBV3Q7PCVDTQDRAFMZKB5ST","short_pith_number":"pith:C5WQBV3Q","schema_version":"1.0","canonical_sha256":"176d00d770fbc551ce03880acca83d94dc61d58b050f9c855422393018996292","source":{"kind":"arxiv","id":"2311.16241","version":1},"attestation_state":"computed","paper":{"title":"SemiVL: Semi-Supervised Semantic Segmentation with Vision-Language Guidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"David Joseph Tan, Federico Tombari, Luc Van Gool, Lukas Hoyer, Muhammad Ferjad Naeem","submitted_at":"2023-11-27T19:00:06Z","abstract_excerpt":"In semi-supervised semantic segmentation, a model is trained with a limited number of labeled images along with a large corpus of unlabeled images to reduce the high annotation effort. While previous methods are able to learn good segmentation boundaries, they are prone to confuse classes with similar visual appearance due to the limited supervision. On the other hand, vision-language models (VLMs) are able to learn diverse semantic knowledge from image-caption datasets but produce noisy segmentation due to the image-level training. In SemiVL, we propose to integrate rich priors from VLM pre-t"},"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":"2311.16241","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-27T19:00:06Z","cross_cats_sorted":[],"title_canon_sha256":"e0f449e893907678ffa426b3a268e7e98a5ffd631b506be613a54504a4d8d13e","abstract_canon_sha256":"60bc1ab944acfe98d004bd9b0aeec0d18141ddbdd3872d4b97c39434b6b30de9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:17:38.340015Z","signature_b64":"4x8wARvlT1c8wXCOKB3mWO9M5jzYQ9GNXgy6ZDRw2zpOixQAImIpYlZ/Mh1BK3sbIg1YIqISZ32lV/BobFvACw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"176d00d770fbc551ce03880acca83d94dc61d58b050f9c855422393018996292","last_reissued_at":"2026-07-05T07:17:38.339492Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:17:38.339492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SemiVL: Semi-Supervised Semantic Segmentation with Vision-Language Guidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"David Joseph Tan, Federico Tombari, Luc Van Gool, Lukas Hoyer, Muhammad Ferjad Naeem","submitted_at":"2023-11-27T19:00:06Z","abstract_excerpt":"In semi-supervised semantic segmentation, a model is trained with a limited number of labeled images along with a large corpus of unlabeled images to reduce the high annotation effort. While previous methods are able to learn good segmentation boundaries, they are prone to confuse classes with similar visual appearance due to the limited supervision. On the other hand, vision-language models (VLMs) are able to learn diverse semantic knowledge from image-caption datasets but produce noisy segmentation due to the image-level training. In SemiVL, we propose to integrate rich priors from VLM pre-t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.16241","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/2311.16241/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":"2311.16241","created_at":"2026-07-05T07:17:38.339548+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.16241v1","created_at":"2026-07-05T07:17:38.339548+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.16241","created_at":"2026-07-05T07:17:38.339548+00:00"},{"alias_kind":"pith_short_12","alias_value":"C5WQBV3Q7PCV","created_at":"2026-07-05T07:17:38.339548+00:00"},{"alias_kind":"pith_short_16","alias_value":"C5WQBV3Q7PCVDTQD","created_at":"2026-07-05T07:17:38.339548+00:00"},{"alias_kind":"pith_short_8","alias_value":"C5WQBV3Q","created_at":"2026-07-05T07:17:38.339548+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30577","citing_title":"APRIL-MedSeg: A Modular Medical Image Segmentation Toolbox Embracing Modern Paradigms","ref_index":263,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30577","citing_title":"APRIL-MedSeg: A Modular Medical Image Segmentation Toolbox Embracing Modern Paradigms","ref_index":93,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C5WQBV3Q7PCVDTQDRAFMZKB5ST","json":"https://pith.science/pith/C5WQBV3Q7PCVDTQDRAFMZKB5ST.json","graph_json":"https://pith.science/api/pith-number/C5WQBV3Q7PCVDTQDRAFMZKB5ST/graph.json","events_json":"https://pith.science/api/pith-number/C5WQBV3Q7PCVDTQDRAFMZKB5ST/events.json","paper":"https://pith.science/paper/C5WQBV3Q"},"agent_actions":{"view_html":"https://pith.science/pith/C5WQBV3Q7PCVDTQDRAFMZKB5ST","download_json":"https://pith.science/pith/C5WQBV3Q7PCVDTQDRAFMZKB5ST.json","view_paper":"https://pith.science/paper/C5WQBV3Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.16241&json=true","fetch_graph":"https://pith.science/api/pith-number/C5WQBV3Q7PCVDTQDRAFMZKB5ST/graph.json","fetch_events":"https://pith.science/api/pith-number/C5WQBV3Q7PCVDTQDRAFMZKB5ST/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C5WQBV3Q7PCVDTQDRAFMZKB5ST/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C5WQBV3Q7PCVDTQDRAFMZKB5ST/action/storage_attestation","attest_author":"https://pith.science/pith/C5WQBV3Q7PCVDTQDRAFMZKB5ST/action/author_attestation","sign_citation":"https://pith.science/pith/C5WQBV3Q7PCVDTQDRAFMZKB5ST/action/citation_signature","submit_replication":"https://pith.science/pith/C5WQBV3Q7PCVDTQDRAFMZKB5ST/action/replication_record"}},"created_at":"2026-07-05T07:17:38.339548+00:00","updated_at":"2026-07-05T07:17:38.339548+00:00"}