{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TMVTKX455OZCBTQNAUWYTJDOJW","short_pith_number":"pith:TMVTKX45","schema_version":"1.0","canonical_sha256":"9b2b355f9debb220ce0d052d89a46e4d8b0fff6c4233cfdb79d289d2ba5663af","source":{"kind":"arxiv","id":"2409.11111","version":2},"attestation_state":"computed","paper":{"title":"Few-Shot Domain Adaptation for Learned Image Compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Dong Liu, Haotian Zhang, Li Li, Tianyu Zhang, Yuqi Li","submitted_at":"2024-09-17T12:05:29Z","abstract_excerpt":"Learned image compression (LIC) has achieved state-of-the-art rate-distortion performance, deemed promising for next-generation image compression techniques. However, pre-trained LIC models usually suffer from significant performance degradation when applied to out-of-training-domain images, implying their poor generalization capabilities. To tackle this problem, we propose a few-shot domain adaptation method for LIC by integrating plug-and-play adapters into pre-trained models. Drawing inspiration from the analogy between latent channels and frequency components, we examine domain gaps in LIC"},"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":"2409.11111","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2024-09-17T12:05:29Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"d244786617af28e3fe132a528b31420f1aa627e75136ef4cab7dc0a4aeca4da3","abstract_canon_sha256":"a464ed54f7cc57befeee540f3335862d756565465472c99067d172229fb1566c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:51.801304Z","signature_b64":"SWpqLGFccQ25LVPw1dACC7yJF38WmvZQGL7NAvmcEO5hST19Efjh/c05jhs4qF/AXi3HOyf+O6ptd7oS5fTnAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b2b355f9debb220ce0d052d89a46e4d8b0fff6c4233cfdb79d289d2ba5663af","last_reissued_at":"2026-07-05T10:02:51.800873Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:51.800873Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Few-Shot Domain Adaptation for Learned Image Compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Dong Liu, Haotian Zhang, Li Li, Tianyu Zhang, Yuqi Li","submitted_at":"2024-09-17T12:05:29Z","abstract_excerpt":"Learned image compression (LIC) has achieved state-of-the-art rate-distortion performance, deemed promising for next-generation image compression techniques. However, pre-trained LIC models usually suffer from significant performance degradation when applied to out-of-training-domain images, implying their poor generalization capabilities. To tackle this problem, we propose a few-shot domain adaptation method for LIC by integrating plug-and-play adapters into pre-trained models. Drawing inspiration from the analogy between latent channels and frequency components, we examine domain gaps in LIC"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.11111","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/2409.11111/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":"2409.11111","created_at":"2026-07-05T10:02:51.800930+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.11111v2","created_at":"2026-07-05T10:02:51.800930+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.11111","created_at":"2026-07-05T10:02:51.800930+00:00"},{"alias_kind":"pith_short_12","alias_value":"TMVTKX455OZC","created_at":"2026-07-05T10:02:51.800930+00:00"},{"alias_kind":"pith_short_16","alias_value":"TMVTKX455OZCBTQN","created_at":"2026-07-05T10:02:51.800930+00:00"},{"alias_kind":"pith_short_8","alias_value":"TMVTKX45","created_at":"2026-07-05T10:02:51.800930+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.16727","citing_title":"An Information-Theoretic Regularizer for Lossy Neural Image Compression","ref_index":51,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TMVTKX455OZCBTQNAUWYTJDOJW","json":"https://pith.science/pith/TMVTKX455OZCBTQNAUWYTJDOJW.json","graph_json":"https://pith.science/api/pith-number/TMVTKX455OZCBTQNAUWYTJDOJW/graph.json","events_json":"https://pith.science/api/pith-number/TMVTKX455OZCBTQNAUWYTJDOJW/events.json","paper":"https://pith.science/paper/TMVTKX45"},"agent_actions":{"view_html":"https://pith.science/pith/TMVTKX455OZCBTQNAUWYTJDOJW","download_json":"https://pith.science/pith/TMVTKX455OZCBTQNAUWYTJDOJW.json","view_paper":"https://pith.science/paper/TMVTKX45","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.11111&json=true","fetch_graph":"https://pith.science/api/pith-number/TMVTKX455OZCBTQNAUWYTJDOJW/graph.json","fetch_events":"https://pith.science/api/pith-number/TMVTKX455OZCBTQNAUWYTJDOJW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TMVTKX455OZCBTQNAUWYTJDOJW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TMVTKX455OZCBTQNAUWYTJDOJW/action/storage_attestation","attest_author":"https://pith.science/pith/TMVTKX455OZCBTQNAUWYTJDOJW/action/author_attestation","sign_citation":"https://pith.science/pith/TMVTKX455OZCBTQNAUWYTJDOJW/action/citation_signature","submit_replication":"https://pith.science/pith/TMVTKX455OZCBTQNAUWYTJDOJW/action/replication_record"}},"created_at":"2026-07-05T10:02:51.800930+00:00","updated_at":"2026-07-05T10:02:51.800930+00:00"}