{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LJEMHS53JDVW2JHYPRGCTV3KRA","short_pith_number":"pith:LJEMHS53","schema_version":"1.0","canonical_sha256":"5a48c3cbbb48eb6d24f87c4c29d76a8805a94772d0dade0c755f797cb1be91e3","source":{"kind":"arxiv","id":"2401.12217","version":1},"attestation_state":"computed","paper":{"title":"Exploring Simple Open-Vocabulary Semantic Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Zihang Lai","submitted_at":"2024-01-22T18:59:29Z","abstract_excerpt":"Open-vocabulary semantic segmentation models aim to accurately assign a semantic label to each pixel in an image from a set of arbitrary open-vocabulary texts. In order to learn such pixel-level alignment, current approaches typically rely on a combination of (i) image-level VL model (e.g. CLIP), (ii) ground truth masks, and (iii) custom grouping encoders. In this paper, we introduce S-Seg, a novel model that can achieve surprisingly strong performance without depending on any of the above elements. S-Seg leverages pseudo-mask and language to train a MaskFormer, and can be easily trained from "},"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":"2401.12217","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-22T18:59:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a0cb66d1063c53375da1e0ffa47850b6bf6b3b85c364b3ea98e7b5df0e4cec33","abstract_canon_sha256":"03f8d50eabb577f31ef0055b941820ea6a82b032e58f72b67d4da4c7af344444"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:36:17.091279Z","signature_b64":"G79AR9oHyt034cF5e1Wh6QWnTm86a2cjzOXwI+HCtleYiaUe9uPJEMoIEeCGoGRihEiG1ttmYwhM4hE1rY/PBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a48c3cbbb48eb6d24f87c4c29d76a8805a94772d0dade0c755f797cb1be91e3","last_reissued_at":"2026-07-05T07:36:17.090830Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:36:17.090830Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Simple Open-Vocabulary Semantic Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Zihang Lai","submitted_at":"2024-01-22T18:59:29Z","abstract_excerpt":"Open-vocabulary semantic segmentation models aim to accurately assign a semantic label to each pixel in an image from a set of arbitrary open-vocabulary texts. In order to learn such pixel-level alignment, current approaches typically rely on a combination of (i) image-level VL model (e.g. CLIP), (ii) ground truth masks, and (iii) custom grouping encoders. In this paper, we introduce S-Seg, a novel model that can achieve surprisingly strong performance without depending on any of the above elements. S-Seg leverages pseudo-mask and language to train a MaskFormer, and can be easily trained from "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.12217","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/2401.12217/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":"2401.12217","created_at":"2026-07-05T07:36:17.090879+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.12217v1","created_at":"2026-07-05T07:36:17.090879+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.12217","created_at":"2026-07-05T07:36:17.090879+00:00"},{"alias_kind":"pith_short_12","alias_value":"LJEMHS53JDVW","created_at":"2026-07-05T07:36:17.090879+00:00"},{"alias_kind":"pith_short_16","alias_value":"LJEMHS53JDVW2JHY","created_at":"2026-07-05T07:36:17.090879+00:00"},{"alias_kind":"pith_short_8","alias_value":"LJEMHS53","created_at":"2026-07-05T07:36:17.090879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.23323","citing_title":"FA-Seg: A Fast and Accurate Diffusion-Based Method for Open-Vocabulary Segmentation","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LJEMHS53JDVW2JHYPRGCTV3KRA","json":"https://pith.science/pith/LJEMHS53JDVW2JHYPRGCTV3KRA.json","graph_json":"https://pith.science/api/pith-number/LJEMHS53JDVW2JHYPRGCTV3KRA/graph.json","events_json":"https://pith.science/api/pith-number/LJEMHS53JDVW2JHYPRGCTV3KRA/events.json","paper":"https://pith.science/paper/LJEMHS53"},"agent_actions":{"view_html":"https://pith.science/pith/LJEMHS53JDVW2JHYPRGCTV3KRA","download_json":"https://pith.science/pith/LJEMHS53JDVW2JHYPRGCTV3KRA.json","view_paper":"https://pith.science/paper/LJEMHS53","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.12217&json=true","fetch_graph":"https://pith.science/api/pith-number/LJEMHS53JDVW2JHYPRGCTV3KRA/graph.json","fetch_events":"https://pith.science/api/pith-number/LJEMHS53JDVW2JHYPRGCTV3KRA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LJEMHS53JDVW2JHYPRGCTV3KRA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LJEMHS53JDVW2JHYPRGCTV3KRA/action/storage_attestation","attest_author":"https://pith.science/pith/LJEMHS53JDVW2JHYPRGCTV3KRA/action/author_attestation","sign_citation":"https://pith.science/pith/LJEMHS53JDVW2JHYPRGCTV3KRA/action/citation_signature","submit_replication":"https://pith.science/pith/LJEMHS53JDVW2JHYPRGCTV3KRA/action/replication_record"}},"created_at":"2026-07-05T07:36:17.090879+00:00","updated_at":"2026-07-05T07:36:17.090879+00:00"}