{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:54MIDHFPATQP4T3IXIYGF4ERMT","short_pith_number":"pith:54MIDHFP","schema_version":"1.0","canonical_sha256":"ef18819caf04e0fe4f68ba3062f09164c14116add31661df7d7e3715a8d05265","source":{"kind":"arxiv","id":"2408.01835","version":1},"attestation_state":"computed","paper":{"title":"TS-SAM: Fine-Tuning Segment-Anything Model for Downstream Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Xu, Kai Wang, Yang Yu","submitted_at":"2024-08-03T18:08:51Z","abstract_excerpt":"Adapter based fine-tuning has been studied for improving the performance of SAM on downstream tasks. However, there is still a significant performance gap between fine-tuned SAMs and domain-specific models. To reduce the gap, we propose Two-Stream SAM (TS-SAM). On the one hand, inspired by the side network in Parameter-Efficient Fine-Tuning (PEFT), we designed a lightweight Convolutional Side Adapter (CSA), which integrates the powerful features from SAM into side network training for comprehensive feature fusion. On the other hand, in line with the characteristics of segmentation tasks, we de"},"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":"2408.01835","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-03T18:08:51Z","cross_cats_sorted":[],"title_canon_sha256":"3ea877d830e4c4d9bc5fd3fdaab03caf21039102180920af791c69623ead4075","abstract_canon_sha256":"cdf9c034b563bf07d7bb926d5f67b9acecfca379ea79dcb8620bef30427a9aa7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:52:03.740760Z","signature_b64":"gPEvOmt7X6Z+gCzrTkadYRSIRVfKbbcBVn5ckNTDmF/LtAUoWbZUboAjSExopatlwj+mYE+ZlN39picNBqSYDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef18819caf04e0fe4f68ba3062f09164c14116add31661df7d7e3715a8d05265","last_reissued_at":"2026-07-05T08:52:03.740269Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:52:03.740269Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TS-SAM: Fine-Tuning Segment-Anything Model for Downstream Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Xu, Kai Wang, Yang Yu","submitted_at":"2024-08-03T18:08:51Z","abstract_excerpt":"Adapter based fine-tuning has been studied for improving the performance of SAM on downstream tasks. However, there is still a significant performance gap between fine-tuned SAMs and domain-specific models. To reduce the gap, we propose Two-Stream SAM (TS-SAM). On the one hand, inspired by the side network in Parameter-Efficient Fine-Tuning (PEFT), we designed a lightweight Convolutional Side Adapter (CSA), which integrates the powerful features from SAM into side network training for comprehensive feature fusion. On the other hand, in line with the characteristics of segmentation tasks, we de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.01835","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/2408.01835/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":"2408.01835","created_at":"2026-07-05T08:52:03.740339+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.01835v1","created_at":"2026-07-05T08:52:03.740339+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.01835","created_at":"2026-07-05T08:52:03.740339+00:00"},{"alias_kind":"pith_short_12","alias_value":"54MIDHFPATQP","created_at":"2026-07-05T08:52:03.740339+00:00"},{"alias_kind":"pith_short_16","alias_value":"54MIDHFPATQP4T3I","created_at":"2026-07-05T08:52:03.740339+00:00"},{"alias_kind":"pith_short_8","alias_value":"54MIDHFP","created_at":"2026-07-05T08:52:03.740339+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.03577","citing_title":"From Local Matches to Global Masks: Template-Guided Instance Detection and Segmentation in Open-World Scenes","ref_index":49,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/54MIDHFPATQP4T3IXIYGF4ERMT","json":"https://pith.science/pith/54MIDHFPATQP4T3IXIYGF4ERMT.json","graph_json":"https://pith.science/api/pith-number/54MIDHFPATQP4T3IXIYGF4ERMT/graph.json","events_json":"https://pith.science/api/pith-number/54MIDHFPATQP4T3IXIYGF4ERMT/events.json","paper":"https://pith.science/paper/54MIDHFP"},"agent_actions":{"view_html":"https://pith.science/pith/54MIDHFPATQP4T3IXIYGF4ERMT","download_json":"https://pith.science/pith/54MIDHFPATQP4T3IXIYGF4ERMT.json","view_paper":"https://pith.science/paper/54MIDHFP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.01835&json=true","fetch_graph":"https://pith.science/api/pith-number/54MIDHFPATQP4T3IXIYGF4ERMT/graph.json","fetch_events":"https://pith.science/api/pith-number/54MIDHFPATQP4T3IXIYGF4ERMT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/54MIDHFPATQP4T3IXIYGF4ERMT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/54MIDHFPATQP4T3IXIYGF4ERMT/action/storage_attestation","attest_author":"https://pith.science/pith/54MIDHFPATQP4T3IXIYGF4ERMT/action/author_attestation","sign_citation":"https://pith.science/pith/54MIDHFPATQP4T3IXIYGF4ERMT/action/citation_signature","submit_replication":"https://pith.science/pith/54MIDHFPATQP4T3IXIYGF4ERMT/action/replication_record"}},"created_at":"2026-07-05T08:52:03.740339+00:00","updated_at":"2026-07-05T08:52:03.740339+00:00"}