{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ME6ID3OS6WYK764OYWRWKIGBOB","short_pith_number":"pith:ME6ID3OS","schema_version":"1.0","canonical_sha256":"613c81edd2f5b0affb8ec5a36520c1705c17627f7bdb953d589888e9e9122b3a","source":{"kind":"arxiv","id":"2207.02066","version":1},"attestation_state":"computed","paper":{"title":"Test-time Adaptation for Real Image Denoising via Meta-transfer Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Agus Gunawan, Muhammad Adi Nugroho, Se Jin Park","submitted_at":"2022-07-05T14:17:35Z","abstract_excerpt":"In recent years, a ton of research has been conducted on real image denoising tasks. However, the efforts are more focused on improving real image denoising through creating a better network architecture. We explore a different direction where we propose to improve real image denoising performance through a better learning strategy that can enable test-time adaptation on the multi-task network. The learning strategy is two stages where the first stage pre-train the network using meta-auxiliary learning to get better meta-initialization. Meanwhile, we use meta-learning for fine-tuning (meta-tra"},"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":"2207.02066","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-07-05T14:17:35Z","cross_cats_sorted":[],"title_canon_sha256":"2f4fda882213720697375959f0c1eca3292cf320bd942e15bb61cc8fa983209f","abstract_canon_sha256":"76f4949854e77b2a315235d9ba65749c82089a259037bb5aebbbc787845c1f57"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:37:47.054786Z","signature_b64":"ljc6q4xAsA2PTMvnUqg8EjEEaO30HQ0FuxUlYI4NKzdJtIP+NaFfcPvRJ+kV/NAaazGkzhtrRUJ+Mf6gGVsDDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"613c81edd2f5b0affb8ec5a36520c1705c17627f7bdb953d589888e9e9122b3a","last_reissued_at":"2026-07-05T04:37:47.054413Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:37:47.054413Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Test-time Adaptation for Real Image Denoising via Meta-transfer Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Agus Gunawan, Muhammad Adi Nugroho, Se Jin Park","submitted_at":"2022-07-05T14:17:35Z","abstract_excerpt":"In recent years, a ton of research has been conducted on real image denoising tasks. However, the efforts are more focused on improving real image denoising through creating a better network architecture. We explore a different direction where we propose to improve real image denoising performance through a better learning strategy that can enable test-time adaptation on the multi-task network. The learning strategy is two stages where the first stage pre-train the network using meta-auxiliary learning to get better meta-initialization. Meanwhile, we use meta-learning for fine-tuning (meta-tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.02066","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/2207.02066/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":"2207.02066","created_at":"2026-07-05T04:37:47.054468+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.02066v1","created_at":"2026-07-05T04:37:47.054468+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.02066","created_at":"2026-07-05T04:37:47.054468+00:00"},{"alias_kind":"pith_short_12","alias_value":"ME6ID3OS6WYK","created_at":"2026-07-05T04:37:47.054468+00:00"},{"alias_kind":"pith_short_16","alias_value":"ME6ID3OS6WYK764O","created_at":"2026-07-05T04:37:47.054468+00:00"},{"alias_kind":"pith_short_8","alias_value":"ME6ID3OS","created_at":"2026-07-05T04:37:47.054468+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.10651","citing_title":"LAN: Learning to Adapt Noise for Image Denoising","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ME6ID3OS6WYK764OYWRWKIGBOB","json":"https://pith.science/pith/ME6ID3OS6WYK764OYWRWKIGBOB.json","graph_json":"https://pith.science/api/pith-number/ME6ID3OS6WYK764OYWRWKIGBOB/graph.json","events_json":"https://pith.science/api/pith-number/ME6ID3OS6WYK764OYWRWKIGBOB/events.json","paper":"https://pith.science/paper/ME6ID3OS"},"agent_actions":{"view_html":"https://pith.science/pith/ME6ID3OS6WYK764OYWRWKIGBOB","download_json":"https://pith.science/pith/ME6ID3OS6WYK764OYWRWKIGBOB.json","view_paper":"https://pith.science/paper/ME6ID3OS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.02066&json=true","fetch_graph":"https://pith.science/api/pith-number/ME6ID3OS6WYK764OYWRWKIGBOB/graph.json","fetch_events":"https://pith.science/api/pith-number/ME6ID3OS6WYK764OYWRWKIGBOB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ME6ID3OS6WYK764OYWRWKIGBOB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ME6ID3OS6WYK764OYWRWKIGBOB/action/storage_attestation","attest_author":"https://pith.science/pith/ME6ID3OS6WYK764OYWRWKIGBOB/action/author_attestation","sign_citation":"https://pith.science/pith/ME6ID3OS6WYK764OYWRWKIGBOB/action/citation_signature","submit_replication":"https://pith.science/pith/ME6ID3OS6WYK764OYWRWKIGBOB/action/replication_record"}},"created_at":"2026-07-05T04:37:47.054468+00:00","updated_at":"2026-07-05T04:37:47.054468+00:00"}