{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PSDBSNUHMEWQ2CO4NBF6H7QHN6","short_pith_number":"pith:PSDBSNUH","schema_version":"1.0","canonical_sha256":"7c86193687612d0d09dc684be3fe076fae7e407d91909381922b3a72c0155c35","source":{"kind":"arxiv","id":"2409.08468","version":1},"attestation_state":"computed","paper":{"title":"Generalization Boosted Adapter for Open-Vocabulary Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changwei Wang, Li Guo, Longzhao Huang, Rongtao Xu, Shibiao Xu, Wenhao Xu, Xuxiang Feng, Zherui Zhang","submitted_at":"2024-09-13T01:49:12Z","abstract_excerpt":"Vision-language models (VLMs) have demonstrated remarkable open-vocabulary object recognition capabilities, motivating their adaptation for dense prediction tasks like segmentation. However, directly applying VLMs to such tasks remains challenging due to their lack of pixel-level granularity and the limited data available for fine-tuning, leading to overfitting and poor generalization. To address these limitations, we propose Generalization Boosted Adapter (GBA), a novel adapter strategy that enhances the generalization and robustness of VLMs for open-vocabulary segmentation. GBA comprises two"},"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":"2409.08468","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-13T01:49:12Z","cross_cats_sorted":[],"title_canon_sha256":"bae74d9c14c30aebf765b44196561bb131d62a7b477b0e9b046e81931bd7c884","abstract_canon_sha256":"cd6ed9ec77c9088c307fda83bc4542c0eb8d754ba8141993e69df48974d525bc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:06:31.836588Z","signature_b64":"iqSM/P6ypBDvEk24VksJ0mzoP6JRrQ3Y3tEHDGg6I2G8l+52e+4vXmaINqm3LcWyhwrqIzR95GoHKVZb0P+qDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c86193687612d0d09dc684be3fe076fae7e407d91909381922b3a72c0155c35","last_reissued_at":"2026-07-05T09:06:31.836140Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:06:31.836140Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generalization Boosted Adapter for Open-Vocabulary Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changwei Wang, Li Guo, Longzhao Huang, Rongtao Xu, Shibiao Xu, Wenhao Xu, Xuxiang Feng, Zherui Zhang","submitted_at":"2024-09-13T01:49:12Z","abstract_excerpt":"Vision-language models (VLMs) have demonstrated remarkable open-vocabulary object recognition capabilities, motivating their adaptation for dense prediction tasks like segmentation. However, directly applying VLMs to such tasks remains challenging due to their lack of pixel-level granularity and the limited data available for fine-tuning, leading to overfitting and poor generalization. To address these limitations, we propose Generalization Boosted Adapter (GBA), a novel adapter strategy that enhances the generalization and robustness of VLMs for open-vocabulary segmentation. GBA comprises two"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.08468","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/2409.08468/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":"2409.08468","created_at":"2026-07-05T09:06:31.836204+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.08468v1","created_at":"2026-07-05T09:06:31.836204+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.08468","created_at":"2026-07-05T09:06:31.836204+00:00"},{"alias_kind":"pith_short_12","alias_value":"PSDBSNUHMEWQ","created_at":"2026-07-05T09:06:31.836204+00:00"},{"alias_kind":"pith_short_16","alias_value":"PSDBSNUHMEWQ2CO4","created_at":"2026-07-05T09:06:31.836204+00:00"},{"alias_kind":"pith_short_8","alias_value":"PSDBSNUH","created_at":"2026-07-05T09:06:31.836204+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/PSDBSNUHMEWQ2CO4NBF6H7QHN6","json":"https://pith.science/pith/PSDBSNUHMEWQ2CO4NBF6H7QHN6.json","graph_json":"https://pith.science/api/pith-number/PSDBSNUHMEWQ2CO4NBF6H7QHN6/graph.json","events_json":"https://pith.science/api/pith-number/PSDBSNUHMEWQ2CO4NBF6H7QHN6/events.json","paper":"https://pith.science/paper/PSDBSNUH"},"agent_actions":{"view_html":"https://pith.science/pith/PSDBSNUHMEWQ2CO4NBF6H7QHN6","download_json":"https://pith.science/pith/PSDBSNUHMEWQ2CO4NBF6H7QHN6.json","view_paper":"https://pith.science/paper/PSDBSNUH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.08468&json=true","fetch_graph":"https://pith.science/api/pith-number/PSDBSNUHMEWQ2CO4NBF6H7QHN6/graph.json","fetch_events":"https://pith.science/api/pith-number/PSDBSNUHMEWQ2CO4NBF6H7QHN6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PSDBSNUHMEWQ2CO4NBF6H7QHN6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PSDBSNUHMEWQ2CO4NBF6H7QHN6/action/storage_attestation","attest_author":"https://pith.science/pith/PSDBSNUHMEWQ2CO4NBF6H7QHN6/action/author_attestation","sign_citation":"https://pith.science/pith/PSDBSNUHMEWQ2CO4NBF6H7QHN6/action/citation_signature","submit_replication":"https://pith.science/pith/PSDBSNUHMEWQ2CO4NBF6H7QHN6/action/replication_record"}},"created_at":"2026-07-05T09:06:31.836204+00:00","updated_at":"2026-07-05T09:06:31.836204+00:00"}