{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:2HEG4I77UIOGXE6BDRRK3H6S7G","short_pith_number":"pith:2HEG4I77","schema_version":"1.0","canonical_sha256":"d1c86e23ffa21c6b93c11c62ad9fd2f992b436956378a6b56c8cd05e18d86de7","source":{"kind":"arxiv","id":"2101.08525","version":2},"attestation_state":"computed","paper":{"title":"GhostSR: Learning Ghost Features for Efficient Image Super-Resolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Chuanjian Liu, Kai Han, Ying Nie, Yunhe Wang, Zhenhua Liu","submitted_at":"2021-01-21T10:09:47Z","abstract_excerpt":"Modern single image super-resolution (SISR) system based on convolutional neural networks (CNNs) achieves fancy performance while requires huge computational costs. The problem on feature redundancy is well studied in visual recognition task, but rarely discussed in SISR. Based on the observation that many features in SISR models are also similar to each other, we propose to use shift operation to generate the redundant features (i.e., ghost features). Compared with depth-wise convolution which is time-consuming on GPU-like devices, shift operation can bring a practical inference acceleration "},"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":"2101.08525","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2021-01-21T10:09:47Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"98b895ac682795240edb9d364aa8ce4fd43005fae4c989b18a746ba23ec8348a","abstract_canon_sha256":"a4f78cb63756372073ae5d487fe4483ca3779c8d2a233b6a160a39f2ab84af96"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:49:10.444271Z","signature_b64":"s10mI9pxveBiR1UkOagOKzkI60JwC+BWsJEpJuRvgO/nCqDSSlrEFE52BRVDrjpY7+8h45/3yBQgw++LIVP0CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d1c86e23ffa21c6b93c11c62ad9fd2f992b436956378a6b56c8cd05e18d86de7","last_reissued_at":"2026-07-05T04:49:10.443863Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:49:10.443863Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GhostSR: Learning Ghost Features for Efficient Image Super-Resolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Chuanjian Liu, Kai Han, Ying Nie, Yunhe Wang, Zhenhua Liu","submitted_at":"2021-01-21T10:09:47Z","abstract_excerpt":"Modern single image super-resolution (SISR) system based on convolutional neural networks (CNNs) achieves fancy performance while requires huge computational costs. The problem on feature redundancy is well studied in visual recognition task, but rarely discussed in SISR. Based on the observation that many features in SISR models are also similar to each other, we propose to use shift operation to generate the redundant features (i.e., ghost features). Compared with depth-wise convolution which is time-consuming on GPU-like devices, shift operation can bring a practical inference acceleration "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.08525","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/2101.08525/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":"2101.08525","created_at":"2026-07-05T04:49:10.443909+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.08525v2","created_at":"2026-07-05T04:49:10.443909+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.08525","created_at":"2026-07-05T04:49:10.443909+00:00"},{"alias_kind":"pith_short_12","alias_value":"2HEG4I77UIOG","created_at":"2026-07-05T04:49:10.443909+00:00"},{"alias_kind":"pith_short_16","alias_value":"2HEG4I77UIOGXE6B","created_at":"2026-07-05T04:49:10.443909+00:00"},{"alias_kind":"pith_short_8","alias_value":"2HEG4I77","created_at":"2026-07-05T04:49:10.443909+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/2HEG4I77UIOGXE6BDRRK3H6S7G","json":"https://pith.science/pith/2HEG4I77UIOGXE6BDRRK3H6S7G.json","graph_json":"https://pith.science/api/pith-number/2HEG4I77UIOGXE6BDRRK3H6S7G/graph.json","events_json":"https://pith.science/api/pith-number/2HEG4I77UIOGXE6BDRRK3H6S7G/events.json","paper":"https://pith.science/paper/2HEG4I77"},"agent_actions":{"view_html":"https://pith.science/pith/2HEG4I77UIOGXE6BDRRK3H6S7G","download_json":"https://pith.science/pith/2HEG4I77UIOGXE6BDRRK3H6S7G.json","view_paper":"https://pith.science/paper/2HEG4I77","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.08525&json=true","fetch_graph":"https://pith.science/api/pith-number/2HEG4I77UIOGXE6BDRRK3H6S7G/graph.json","fetch_events":"https://pith.science/api/pith-number/2HEG4I77UIOGXE6BDRRK3H6S7G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2HEG4I77UIOGXE6BDRRK3H6S7G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2HEG4I77UIOGXE6BDRRK3H6S7G/action/storage_attestation","attest_author":"https://pith.science/pith/2HEG4I77UIOGXE6BDRRK3H6S7G/action/author_attestation","sign_citation":"https://pith.science/pith/2HEG4I77UIOGXE6BDRRK3H6S7G/action/citation_signature","submit_replication":"https://pith.science/pith/2HEG4I77UIOGXE6BDRRK3H6S7G/action/replication_record"}},"created_at":"2026-07-05T04:49:10.443909+00:00","updated_at":"2026-07-05T04:49:10.443909+00:00"}