{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:C67OGVU6EK3AESNNO4JB4OXLTU","short_pith_number":"pith:C67OGVU6","schema_version":"1.0","canonical_sha256":"17bee3569e22b60249ad77121e3aeb9d35b9407b9741369ac42023dd98060a82","source":{"kind":"arxiv","id":"2412.08939","version":2},"attestation_state":"computed","paper":{"title":"Dynamic Contrastive Knowledge Distillation for Efficient Image Restoration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiao Xie, Jie Hu, Jincheng Liao, Junbo Qiao, Shaohui Lin, Simiao Li, Wei Li, Yunhang Shen, Yunshuai Zhou","submitted_at":"2024-12-12T05:01:17Z","abstract_excerpt":"Knowledge distillation (KD) is a valuable yet challenging approach that enhances a compact student network by learning from a high-performance but cumbersome teacher model. However, previous KD methods for image restoration overlook the state of the student during the distillation, adopting a fixed solution space that limits the capability of KD. Additionally, relying solely on L1-type loss struggles to leverage the distribution information of images. In this work, we propose a novel dynamic contrastive knowledge distillation (DCKD) framework for image restoration. Specifically, we introduce d"},"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":"2412.08939","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T05:01:17Z","cross_cats_sorted":[],"title_canon_sha256":"c6d0973494e2fbc531416611b9b451f563329c5f2d3cb636dd6d6dd7337d0bf6","abstract_canon_sha256":"b702a5c2f096b6ce85a30cae0eb72467b7bb55b2f06ec68658508b06f7479ff0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:50:08.337748Z","signature_b64":"j4J+9ecICoKq5ocezk5pAYx+i7zYUxUwcAeEVJHAnC50yxLeDL/boYIfLxas22+DqwA3zDQWSwf+h0PrEornBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17bee3569e22b60249ad77121e3aeb9d35b9407b9741369ac42023dd98060a82","last_reissued_at":"2026-07-05T09:50:08.337127Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:50:08.337127Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dynamic Contrastive Knowledge Distillation for Efficient Image Restoration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiao Xie, Jie Hu, Jincheng Liao, Junbo Qiao, Shaohui Lin, Simiao Li, Wei Li, Yunhang Shen, Yunshuai Zhou","submitted_at":"2024-12-12T05:01:17Z","abstract_excerpt":"Knowledge distillation (KD) is a valuable yet challenging approach that enhances a compact student network by learning from a high-performance but cumbersome teacher model. However, previous KD methods for image restoration overlook the state of the student during the distillation, adopting a fixed solution space that limits the capability of KD. Additionally, relying solely on L1-type loss struggles to leverage the distribution information of images. In this work, we propose a novel dynamic contrastive knowledge distillation (DCKD) framework for image restoration. Specifically, we introduce d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08939","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/2412.08939/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":"2412.08939","created_at":"2026-07-05T09:50:08.337217+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.08939v2","created_at":"2026-07-05T09:50:08.337217+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08939","created_at":"2026-07-05T09:50:08.337217+00:00"},{"alias_kind":"pith_short_12","alias_value":"C67OGVU6EK3A","created_at":"2026-07-05T09:50:08.337217+00:00"},{"alias_kind":"pith_short_16","alias_value":"C67OGVU6EK3AESNN","created_at":"2026-07-05T09:50:08.337217+00:00"},{"alias_kind":"pith_short_8","alias_value":"C67OGVU6","created_at":"2026-07-05T09:50:08.337217+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/C67OGVU6EK3AESNNO4JB4OXLTU","json":"https://pith.science/pith/C67OGVU6EK3AESNNO4JB4OXLTU.json","graph_json":"https://pith.science/api/pith-number/C67OGVU6EK3AESNNO4JB4OXLTU/graph.json","events_json":"https://pith.science/api/pith-number/C67OGVU6EK3AESNNO4JB4OXLTU/events.json","paper":"https://pith.science/paper/C67OGVU6"},"agent_actions":{"view_html":"https://pith.science/pith/C67OGVU6EK3AESNNO4JB4OXLTU","download_json":"https://pith.science/pith/C67OGVU6EK3AESNNO4JB4OXLTU.json","view_paper":"https://pith.science/paper/C67OGVU6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.08939&json=true","fetch_graph":"https://pith.science/api/pith-number/C67OGVU6EK3AESNNO4JB4OXLTU/graph.json","fetch_events":"https://pith.science/api/pith-number/C67OGVU6EK3AESNNO4JB4OXLTU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C67OGVU6EK3AESNNO4JB4OXLTU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C67OGVU6EK3AESNNO4JB4OXLTU/action/storage_attestation","attest_author":"https://pith.science/pith/C67OGVU6EK3AESNNO4JB4OXLTU/action/author_attestation","sign_citation":"https://pith.science/pith/C67OGVU6EK3AESNNO4JB4OXLTU/action/citation_signature","submit_replication":"https://pith.science/pith/C67OGVU6EK3AESNNO4JB4OXLTU/action/replication_record"}},"created_at":"2026-07-05T09:50:08.337217+00:00","updated_at":"2026-07-05T09:50:08.337217+00:00"}