{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PT2J4PCNAHODBVPNR7TNCYZAWX","short_pith_number":"pith:PT2J4PCN","schema_version":"1.0","canonical_sha256":"7cf49e3c4d01dc30d5ed8fe6d16320b5c07aa5efeb227184cd4477327542c82b","source":{"kind":"arxiv","id":"2503.06042","version":2},"attestation_state":"computed","paper":{"title":"Improving SAM for Camouflaged Object Detection via Dual Stream Adapters","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guihai Chen, Jiaming Liu, Linghe Kong","submitted_at":"2025-03-08T03:39:03Z","abstract_excerpt":"Segment anything model (SAM) has shown impressive general-purpose segmentation performance on natural images, but its performance on camouflaged object detection (COD) is unsatisfactory. In this paper, we propose SAM-COD that performs camouflaged object detection for RGB-D inputs. While keeping the SAM architecture intact, dual stream adapters are expanded on the image encoder to learn potential complementary information from RGB images and depth images, and fine-tune the mask decoder and its depth replica to perform dual-stream mask prediction. In practice, the dual stream adapters are embedd"},"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":"2503.06042","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-08T03:39:03Z","cross_cats_sorted":[],"title_canon_sha256":"484386802bf4edbd3c7540f2099455a009a38e252711f2842f363f15e37d73df","abstract_canon_sha256":"60c6e1f91937108708cfea15baa122b9dd7800c3fd6a45d8c9b60b510feb1928"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:40:39.134415Z","signature_b64":"ndmWCoxEWGEUpBQYBeB6Q+4JqLHj+IBYgMcJjN3oZxb76U94UeLoEVW00YTqtbJXts3ycyjx7lYgu2Z4lepWAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7cf49e3c4d01dc30d5ed8fe6d16320b5c07aa5efeb227184cd4477327542c82b","last_reissued_at":"2026-07-05T10:40:39.133845Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:40:39.133845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving SAM for Camouflaged Object Detection via Dual Stream Adapters","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guihai Chen, Jiaming Liu, Linghe Kong","submitted_at":"2025-03-08T03:39:03Z","abstract_excerpt":"Segment anything model (SAM) has shown impressive general-purpose segmentation performance on natural images, but its performance on camouflaged object detection (COD) is unsatisfactory. In this paper, we propose SAM-COD that performs camouflaged object detection for RGB-D inputs. While keeping the SAM architecture intact, dual stream adapters are expanded on the image encoder to learn potential complementary information from RGB images and depth images, and fine-tune the mask decoder and its depth replica to perform dual-stream mask prediction. In practice, the dual stream adapters are embedd"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.06042","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/2503.06042/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":"2503.06042","created_at":"2026-07-05T10:40:39.133906+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.06042v2","created_at":"2026-07-05T10:40:39.133906+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.06042","created_at":"2026-07-05T10:40:39.133906+00:00"},{"alias_kind":"pith_short_12","alias_value":"PT2J4PCNAHOD","created_at":"2026-07-05T10:40:39.133906+00:00"},{"alias_kind":"pith_short_16","alias_value":"PT2J4PCNAHODBVPN","created_at":"2026-07-05T10:40:39.133906+00:00"},{"alias_kind":"pith_short_8","alias_value":"PT2J4PCN","created_at":"2026-07-05T10:40:39.133906+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08906","citing_title":"DifferSeg: Towards Diverse Multimodal Binary Segmentation via Differential Perception and Frequency Guidance","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27777","citing_title":"TRUST: Efficient Abdominal Trauma Recognition via Image-to-Ultrasound-Video Transfer Learning","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12380","citing_title":"Modality-Agnostic Prompt Learning for Multi-Modal Camouflaged Object Detection","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16855","citing_title":"When W4A4 Breaks Camouflaged Object Detection: Token-Group Dual-Constraint Activation Quantization","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PT2J4PCNAHODBVPNR7TNCYZAWX","json":"https://pith.science/pith/PT2J4PCNAHODBVPNR7TNCYZAWX.json","graph_json":"https://pith.science/api/pith-number/PT2J4PCNAHODBVPNR7TNCYZAWX/graph.json","events_json":"https://pith.science/api/pith-number/PT2J4PCNAHODBVPNR7TNCYZAWX/events.json","paper":"https://pith.science/paper/PT2J4PCN"},"agent_actions":{"view_html":"https://pith.science/pith/PT2J4PCNAHODBVPNR7TNCYZAWX","download_json":"https://pith.science/pith/PT2J4PCNAHODBVPNR7TNCYZAWX.json","view_paper":"https://pith.science/paper/PT2J4PCN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.06042&json=true","fetch_graph":"https://pith.science/api/pith-number/PT2J4PCNAHODBVPNR7TNCYZAWX/graph.json","fetch_events":"https://pith.science/api/pith-number/PT2J4PCNAHODBVPNR7TNCYZAWX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PT2J4PCNAHODBVPNR7TNCYZAWX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PT2J4PCNAHODBVPNR7TNCYZAWX/action/storage_attestation","attest_author":"https://pith.science/pith/PT2J4PCNAHODBVPNR7TNCYZAWX/action/author_attestation","sign_citation":"https://pith.science/pith/PT2J4PCNAHODBVPNR7TNCYZAWX/action/citation_signature","submit_replication":"https://pith.science/pith/PT2J4PCNAHODBVPNR7TNCYZAWX/action/replication_record"}},"created_at":"2026-07-05T10:40:39.133906+00:00","updated_at":"2026-07-05T10:40:39.133906+00:00"}