{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:U64HBXYOLT6XZKPAUGEUEMTWEK","short_pith_number":"pith:U64HBXYO","schema_version":"1.0","canonical_sha256":"a7b870df0e5cfd7ca9e0a18942327622bcd9bda362a522317badfb662154927c","source":{"kind":"arxiv","id":"2205.05671","version":1},"attestation_state":"computed","paper":{"title":"RepSR: Training Efficient VGG-style Super-Resolution Networks with Structural Re-Parameterization and Batch Normalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Chao Dong, Xintao Wang, Ying Shan","submitted_at":"2022-05-11T17:55:49Z","abstract_excerpt":"This paper explores training efficient VGG-style super-resolution (SR) networks with the structural re-parameterization technique. The general pipeline of re-parameterization is to train networks with multi-branch topology first, and then merge them into standard 3x3 convolutions for efficient inference. In this work, we revisit those primary designs and investigate essential components for re-parameterizing SR networks. First of all, we find that batch normalization (BN) is important to bring training non-linearity and improve the final performance. However, BN is typically ignored in SR, as "},"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":"2205.05671","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-11T17:55:49Z","cross_cats_sorted":["cs.LG","eess.IV"],"title_canon_sha256":"87021164dcc9bc0227e18e91f0b74d9e86d27539a215a9cfd064bf4e65b848da","abstract_canon_sha256":"9f7251b1233830dd70d7ada3a2c3d2e3539b315a79bb257fc52d58f46eb0a85d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:22:28.346789Z","signature_b64":"YymMrUk7VJLCqx//lIp2OCcXbmgMoyD0jf2W1EYiQtXXwzFdj9CKxtgQ9PIcMK0KBiot9xN+8E1g9PpTIAeHBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7b870df0e5cfd7ca9e0a18942327622bcd9bda362a522317badfb662154927c","last_reissued_at":"2026-07-05T04:22:28.346354Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:22:28.346354Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RepSR: Training Efficient VGG-style Super-Resolution Networks with Structural Re-Parameterization and Batch Normalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Chao Dong, Xintao Wang, Ying Shan","submitted_at":"2022-05-11T17:55:49Z","abstract_excerpt":"This paper explores training efficient VGG-style super-resolution (SR) networks with the structural re-parameterization technique. The general pipeline of re-parameterization is to train networks with multi-branch topology first, and then merge them into standard 3x3 convolutions for efficient inference. In this work, we revisit those primary designs and investigate essential components for re-parameterizing SR networks. First of all, we find that batch normalization (BN) is important to bring training non-linearity and improve the final performance. However, BN is typically ignored in SR, as "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.05671","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/2205.05671/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":"2205.05671","created_at":"2026-07-05T04:22:28.346428+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.05671v1","created_at":"2026-07-05T04:22:28.346428+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.05671","created_at":"2026-07-05T04:22:28.346428+00:00"},{"alias_kind":"pith_short_12","alias_value":"U64HBXYOLT6X","created_at":"2026-07-05T04:22:28.346428+00:00"},{"alias_kind":"pith_short_16","alias_value":"U64HBXYOLT6XZKPA","created_at":"2026-07-05T04:22:28.346428+00:00"},{"alias_kind":"pith_short_8","alias_value":"U64HBXYO","created_at":"2026-07-05T04:22:28.346428+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/U64HBXYOLT6XZKPAUGEUEMTWEK","json":"https://pith.science/pith/U64HBXYOLT6XZKPAUGEUEMTWEK.json","graph_json":"https://pith.science/api/pith-number/U64HBXYOLT6XZKPAUGEUEMTWEK/graph.json","events_json":"https://pith.science/api/pith-number/U64HBXYOLT6XZKPAUGEUEMTWEK/events.json","paper":"https://pith.science/paper/U64HBXYO"},"agent_actions":{"view_html":"https://pith.science/pith/U64HBXYOLT6XZKPAUGEUEMTWEK","download_json":"https://pith.science/pith/U64HBXYOLT6XZKPAUGEUEMTWEK.json","view_paper":"https://pith.science/paper/U64HBXYO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.05671&json=true","fetch_graph":"https://pith.science/api/pith-number/U64HBXYOLT6XZKPAUGEUEMTWEK/graph.json","fetch_events":"https://pith.science/api/pith-number/U64HBXYOLT6XZKPAUGEUEMTWEK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U64HBXYOLT6XZKPAUGEUEMTWEK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U64HBXYOLT6XZKPAUGEUEMTWEK/action/storage_attestation","attest_author":"https://pith.science/pith/U64HBXYOLT6XZKPAUGEUEMTWEK/action/author_attestation","sign_citation":"https://pith.science/pith/U64HBXYOLT6XZKPAUGEUEMTWEK/action/citation_signature","submit_replication":"https://pith.science/pith/U64HBXYOLT6XZKPAUGEUEMTWEK/action/replication_record"}},"created_at":"2026-07-05T04:22:28.346428+00:00","updated_at":"2026-07-05T04:22:28.346428+00:00"}