{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TAWHO7YTRA7J46UNIHD5CFU6WV","short_pith_number":"pith:TAWHO7YT","schema_version":"1.0","canonical_sha256":"982c777f13883e9e7a8d41c7d1169eb55f01c9930b1e36bf47200b76c6eaada5","source":{"kind":"arxiv","id":"2311.15537","version":2},"attestation_state":"computed","paper":{"title":"SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Xie, Fahad Shahbaz Khan, Jiale Cao, Jin Xie, Yanwei Pang","submitted_at":"2023-11-27T05:00:38Z","abstract_excerpt":"Open-vocabulary semantic segmentation strives to distinguish pixels into different semantic groups from an open set of categories. Most existing methods explore utilizing pre-trained vision-language models, in which the key is to adopt the image-level model for pixel-level segmentation task. In this paper, we propose a simple encoder-decoder, named SED, for open-vocabulary semantic segmentation, which comprises a hierarchical encoder-based cost map generation and a gradual fusion decoder with category early rejection. The hierarchical encoder-based cost map generation employs hierarchical back"},"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":"2311.15537","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-27T05:00:38Z","cross_cats_sorted":[],"title_canon_sha256":"7affc876a8ee8197054298a6b6367adb4a304ca3a18c307836cf76aa2b59fa89","abstract_canon_sha256":"abcd6ccf0b38ce30fe1f94526a8ea042ce5af2d6c086d7f2ea381dd3a4c21727"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:49:35.297398Z","signature_b64":"bwebz/WM+XyyeixkY/5OQ0DHP2ectufoNo71M0+okNagH0/U0qYIuM/jDVoVsaxMPUK5xLwQRSE/L1r3qQCVDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"982c777f13883e9e7a8d41c7d1169eb55f01c9930b1e36bf47200b76c6eaada5","last_reissued_at":"2026-07-05T07:49:35.296766Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:49:35.296766Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Xie, Fahad Shahbaz Khan, Jiale Cao, Jin Xie, Yanwei Pang","submitted_at":"2023-11-27T05:00:38Z","abstract_excerpt":"Open-vocabulary semantic segmentation strives to distinguish pixels into different semantic groups from an open set of categories. Most existing methods explore utilizing pre-trained vision-language models, in which the key is to adopt the image-level model for pixel-level segmentation task. In this paper, we propose a simple encoder-decoder, named SED, for open-vocabulary semantic segmentation, which comprises a hierarchical encoder-based cost map generation and a gradual fusion decoder with category early rejection. The hierarchical encoder-based cost map generation employs hierarchical back"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.15537","kind":"arxiv","version":2},"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/2311.15537/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":"2311.15537","created_at":"2026-07-05T07:49:35.296854+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.15537v2","created_at":"2026-07-05T07:49:35.296854+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.15537","created_at":"2026-07-05T07:49:35.296854+00:00"},{"alias_kind":"pith_short_12","alias_value":"TAWHO7YTRA7J","created_at":"2026-07-05T07:49:35.296854+00:00"},{"alias_kind":"pith_short_16","alias_value":"TAWHO7YTRA7J46UN","created_at":"2026-07-05T07:49:35.296854+00:00"},{"alias_kind":"pith_short_8","alias_value":"TAWHO7YT","created_at":"2026-07-05T07:49:35.296854+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.01275","citing_title":"Novel Category Discovery with X-Agent Attention for Open-Vocabulary Semantic Segmentation","ref_index":48,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TAWHO7YTRA7J46UNIHD5CFU6WV","json":"https://pith.science/pith/TAWHO7YTRA7J46UNIHD5CFU6WV.json","graph_json":"https://pith.science/api/pith-number/TAWHO7YTRA7J46UNIHD5CFU6WV/graph.json","events_json":"https://pith.science/api/pith-number/TAWHO7YTRA7J46UNIHD5CFU6WV/events.json","paper":"https://pith.science/paper/TAWHO7YT"},"agent_actions":{"view_html":"https://pith.science/pith/TAWHO7YTRA7J46UNIHD5CFU6WV","download_json":"https://pith.science/pith/TAWHO7YTRA7J46UNIHD5CFU6WV.json","view_paper":"https://pith.science/paper/TAWHO7YT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.15537&json=true","fetch_graph":"https://pith.science/api/pith-number/TAWHO7YTRA7J46UNIHD5CFU6WV/graph.json","fetch_events":"https://pith.science/api/pith-number/TAWHO7YTRA7J46UNIHD5CFU6WV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TAWHO7YTRA7J46UNIHD5CFU6WV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TAWHO7YTRA7J46UNIHD5CFU6WV/action/storage_attestation","attest_author":"https://pith.science/pith/TAWHO7YTRA7J46UNIHD5CFU6WV/action/author_attestation","sign_citation":"https://pith.science/pith/TAWHO7YTRA7J46UNIHD5CFU6WV/action/citation_signature","submit_replication":"https://pith.science/pith/TAWHO7YTRA7J46UNIHD5CFU6WV/action/replication_record"}},"created_at":"2026-07-05T07:49:35.296854+00:00","updated_at":"2026-07-05T07:49:35.296854+00:00"}