{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:5NRJMANKB5LOEB2NIID3XT256S","short_pith_number":"pith:5NRJMANK","schema_version":"1.0","canonical_sha256":"eb629601aa0f56e2074d4207bbcf5df4bb892e9006b288594af7dfe738df3c25","source":{"kind":"arxiv","id":"2212.09506","version":3},"attestation_state":"computed","paper":{"title":"CLIP is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Binbin Lin, Boxi Wu, Haifeng Liu, Ke Li, Minghao Chen, Wenxiao Wang, Xiaofei He, Yuqi Lin","submitted_at":"2022-12-16T06:23:59Z","abstract_excerpt":"Weakly supervised semantic segmentation (WSSS) with image-level labels is a challenging task. Mainstream approaches follow a multi-stage framework and suffer from high training costs. In this paper, we explore the potential of Contrastive Language-Image Pre-training models (CLIP) to localize different categories with only image-level labels and without further training. To efficiently generate high-quality segmentation masks from CLIP, we propose a novel WSSS framework called CLIP-ES. Our framework improves all three stages of WSSS with special designs for CLIP: 1) We introduce the softmax fun"},"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":"2212.09506","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-16T06:23:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3d89186f996ca01e7623ff714e1a05a1b48c7cd5c7530736fb1120253b9e462b","abstract_canon_sha256":"a8d76c6bd6f7613b83d11ce64d32bc61ecf4fb649105a8e6c62dbdc93eb920d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:53:52.126240Z","signature_b64":"J4j/T9TAFPlky1zE5m/DLDKyuDQnAEnn7N6WvD/gpwTU8TvCios6mqJ/4nP3erPAnDtglgMwEZB1gACroA4qCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb629601aa0f56e2074d4207bbcf5df4bb892e9006b288594af7dfe738df3c25","last_reissued_at":"2026-07-05T05:53:52.125815Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:53:52.125815Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CLIP is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Binbin Lin, Boxi Wu, Haifeng Liu, Ke Li, Minghao Chen, Wenxiao Wang, Xiaofei He, Yuqi Lin","submitted_at":"2022-12-16T06:23:59Z","abstract_excerpt":"Weakly supervised semantic segmentation (WSSS) with image-level labels is a challenging task. Mainstream approaches follow a multi-stage framework and suffer from high training costs. In this paper, we explore the potential of Contrastive Language-Image Pre-training models (CLIP) to localize different categories with only image-level labels and without further training. To efficiently generate high-quality segmentation masks from CLIP, we propose a novel WSSS framework called CLIP-ES. Our framework improves all three stages of WSSS with special designs for CLIP: 1) We introduce the softmax fun"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.09506","kind":"arxiv","version":3},"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/2212.09506/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":"2212.09506","created_at":"2026-07-05T05:53:52.125873+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.09506v3","created_at":"2026-07-05T05:53:52.125873+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.09506","created_at":"2026-07-05T05:53:52.125873+00:00"},{"alias_kind":"pith_short_12","alias_value":"5NRJMANKB5LO","created_at":"2026-07-05T05:53:52.125873+00:00"},{"alias_kind":"pith_short_16","alias_value":"5NRJMANKB5LOEB2N","created_at":"2026-07-05T05:53:52.125873+00:00"},{"alias_kind":"pith_short_8","alias_value":"5NRJMANK","created_at":"2026-07-05T05:53:52.125873+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5NRJMANKB5LOEB2NIID3XT256S","json":"https://pith.science/pith/5NRJMANKB5LOEB2NIID3XT256S.json","graph_json":"https://pith.science/api/pith-number/5NRJMANKB5LOEB2NIID3XT256S/graph.json","events_json":"https://pith.science/api/pith-number/5NRJMANKB5LOEB2NIID3XT256S/events.json","paper":"https://pith.science/paper/5NRJMANK"},"agent_actions":{"view_html":"https://pith.science/pith/5NRJMANKB5LOEB2NIID3XT256S","download_json":"https://pith.science/pith/5NRJMANKB5LOEB2NIID3XT256S.json","view_paper":"https://pith.science/paper/5NRJMANK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.09506&json=true","fetch_graph":"https://pith.science/api/pith-number/5NRJMANKB5LOEB2NIID3XT256S/graph.json","fetch_events":"https://pith.science/api/pith-number/5NRJMANKB5LOEB2NIID3XT256S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5NRJMANKB5LOEB2NIID3XT256S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5NRJMANKB5LOEB2NIID3XT256S/action/storage_attestation","attest_author":"https://pith.science/pith/5NRJMANKB5LOEB2NIID3XT256S/action/author_attestation","sign_citation":"https://pith.science/pith/5NRJMANKB5LOEB2NIID3XT256S/action/citation_signature","submit_replication":"https://pith.science/pith/5NRJMANKB5LOEB2NIID3XT256S/action/replication_record"}},"created_at":"2026-07-05T05:53:52.125873+00:00","updated_at":"2026-07-05T05:53:52.125873+00:00"}