{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TPKZKU4U2OZRNG65ALJB4QDJHV","short_pith_number":"pith:TPKZKU4U","schema_version":"1.0","canonical_sha256":"9bd5955394d3b3169bdd02d21e40693d774cc0c5d8080ebfe12a69f797df949c","source":{"kind":"arxiv","id":"2303.05646","version":1},"attestation_state":"computed","paper":{"title":"Iterative Few-shot Semantic Segmentation from Image Label Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengjie Wang, Haohan Wang, Haoqian Wang, Jiangning Zhang, Liang Liu, Wuhao Zhang, Yabiao Wang, Zhenye Gan","submitted_at":"2023-03-10T01:48:14Z","abstract_excerpt":"Few-shot semantic segmentation aims to learn to segment unseen class objects with the guidance of only a few support images. Most previous methods rely on the pixel-level label of support images. In this paper, we focus on a more challenging setting, in which only the image-level labels are available. We propose a general framework to firstly generate coarse masks with the help of the powerful vision-language model CLIP, and then iteratively and mutually refine the mask predictions of support and query images. Extensive experiments on PASCAL-5i and COCO-20i datasets demonstrate that our method"},"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":"2303.05646","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-10T01:48:14Z","cross_cats_sorted":[],"title_canon_sha256":"f03ec7678a3643c83a095c6658d95e3a34d7d9ff2e9c623e7e0015e61cdab474","abstract_canon_sha256":"2c9b8dde4197abbc09f480394cf3d54d76a6f53e5c9b5d0f1ae7d16826bd3572"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:49:46.111775Z","signature_b64":"FLmMWM2gADuSttJnuqGJeHCiWFwMHMd89T8jmcHYICrwdtSqQaNOCtQp6XHavf5569QUShaHijWPsyTnzyJuCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9bd5955394d3b3169bdd02d21e40693d774cc0c5d8080ebfe12a69f797df949c","last_reissued_at":"2026-07-05T05:49:46.111387Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:49:46.111387Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Iterative Few-shot Semantic Segmentation from Image Label Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengjie Wang, Haohan Wang, Haoqian Wang, Jiangning Zhang, Liang Liu, Wuhao Zhang, Yabiao Wang, Zhenye Gan","submitted_at":"2023-03-10T01:48:14Z","abstract_excerpt":"Few-shot semantic segmentation aims to learn to segment unseen class objects with the guidance of only a few support images. Most previous methods rely on the pixel-level label of support images. In this paper, we focus on a more challenging setting, in which only the image-level labels are available. We propose a general framework to firstly generate coarse masks with the help of the powerful vision-language model CLIP, and then iteratively and mutually refine the mask predictions of support and query images. Extensive experiments on PASCAL-5i and COCO-20i datasets demonstrate that our method"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.05646","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/2303.05646/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":"2303.05646","created_at":"2026-07-05T05:49:46.111452+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.05646v1","created_at":"2026-07-05T05:49:46.111452+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.05646","created_at":"2026-07-05T05:49:46.111452+00:00"},{"alias_kind":"pith_short_12","alias_value":"TPKZKU4U2OZR","created_at":"2026-07-05T05:49:46.111452+00:00"},{"alias_kind":"pith_short_16","alias_value":"TPKZKU4U2OZRNG65","created_at":"2026-07-05T05:49:46.111452+00:00"},{"alias_kind":"pith_short_8","alias_value":"TPKZKU4U","created_at":"2026-07-05T05:49:46.111452+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.16159","citing_title":"Through the Looking Glass: A Dual Perspective on Weakly-Supervised Few-Shot Segmentation","ref_index":51,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TPKZKU4U2OZRNG65ALJB4QDJHV","json":"https://pith.science/pith/TPKZKU4U2OZRNG65ALJB4QDJHV.json","graph_json":"https://pith.science/api/pith-number/TPKZKU4U2OZRNG65ALJB4QDJHV/graph.json","events_json":"https://pith.science/api/pith-number/TPKZKU4U2OZRNG65ALJB4QDJHV/events.json","paper":"https://pith.science/paper/TPKZKU4U"},"agent_actions":{"view_html":"https://pith.science/pith/TPKZKU4U2OZRNG65ALJB4QDJHV","download_json":"https://pith.science/pith/TPKZKU4U2OZRNG65ALJB4QDJHV.json","view_paper":"https://pith.science/paper/TPKZKU4U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.05646&json=true","fetch_graph":"https://pith.science/api/pith-number/TPKZKU4U2OZRNG65ALJB4QDJHV/graph.json","fetch_events":"https://pith.science/api/pith-number/TPKZKU4U2OZRNG65ALJB4QDJHV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TPKZKU4U2OZRNG65ALJB4QDJHV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TPKZKU4U2OZRNG65ALJB4QDJHV/action/storage_attestation","attest_author":"https://pith.science/pith/TPKZKU4U2OZRNG65ALJB4QDJHV/action/author_attestation","sign_citation":"https://pith.science/pith/TPKZKU4U2OZRNG65ALJB4QDJHV/action/citation_signature","submit_replication":"https://pith.science/pith/TPKZKU4U2OZRNG65ALJB4QDJHV/action/replication_record"}},"created_at":"2026-07-05T05:49:46.111452+00:00","updated_at":"2026-07-05T05:49:46.111452+00:00"}