{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:BH35MPFRTPTQD3GVGDJWGVAZZF","short_pith_number":"pith:BH35MPFR","schema_version":"1.0","canonical_sha256":"09f7d63cb19be701ecd530d3635419c949bd7961f26b3dccf0af756b03811d45","source":{"kind":"arxiv","id":"2202.04595","version":4},"attestation_state":"computed","paper":{"title":"Exploring Structural Sparsity in Neural Image Compression","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"eess.IV","authors_text":"Chao Li, Shanzhi Yin, Wei Liu, Wen Tan, Yongsheng Liang, Youneng Bao","submitted_at":"2022-02-09T17:46:49Z","abstract_excerpt":"Neural image compression have reached or out-performed traditional methods (such as JPEG, BPG, WebP). However,their sophisticated network structures with cascaded convolution layers bring heavy computational burden for practical deployment. In this paper, we explore the structural sparsity in neural image compression network to obtain real-time acceleration without any specialized hardware design or algorithm. We propose a simple plug-in adaptive binary channel masking(ABCM) to judge the importance of each convolution channel and introduce sparsity during training. During inference, the unimpo"},"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":"2202.04595","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.IV","submitted_at":"2022-02-09T17:46:49Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"c82f22dcf6c003a05af9966c3bb3dfe37cf40ec54ab3886bd9d0ec159e9ef304","abstract_canon_sha256":"46f3d2142a131dd7fd9a7f8237decf441b9a0bd5f5c3c2b3ab81280d3923e41f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:04:04.139018Z","signature_b64":"QAflZ70KLfbQFU9L4YRdLGs7bqll/D/Kz8VKS0QTwHD9x7ABnbVvFqYS3W14YasEDSTBLZpkOG8HbDmkYjd7AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09f7d63cb19be701ecd530d3635419c949bd7961f26b3dccf0af756b03811d45","last_reissued_at":"2026-07-05T04:04:04.138542Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:04:04.138542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Structural Sparsity in Neural Image Compression","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"eess.IV","authors_text":"Chao Li, Shanzhi Yin, Wei Liu, Wen Tan, Yongsheng Liang, Youneng Bao","submitted_at":"2022-02-09T17:46:49Z","abstract_excerpt":"Neural image compression have reached or out-performed traditional methods (such as JPEG, BPG, WebP). However,their sophisticated network structures with cascaded convolution layers bring heavy computational burden for practical deployment. In this paper, we explore the structural sparsity in neural image compression network to obtain real-time acceleration without any specialized hardware design or algorithm. We propose a simple plug-in adaptive binary channel masking(ABCM) to judge the importance of each convolution channel and introduce sparsity during training. During inference, the unimpo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.04595","kind":"arxiv","version":4},"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/2202.04595/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":"2202.04595","created_at":"2026-07-05T04:04:04.138600+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.04595v4","created_at":"2026-07-05T04:04:04.138600+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.04595","created_at":"2026-07-05T04:04:04.138600+00:00"},{"alias_kind":"pith_short_12","alias_value":"BH35MPFRTPTQ","created_at":"2026-07-05T04:04:04.138600+00:00"},{"alias_kind":"pith_short_16","alias_value":"BH35MPFRTPTQD3GV","created_at":"2026-07-05T04:04:04.138600+00:00"},{"alias_kind":"pith_short_8","alias_value":"BH35MPFR","created_at":"2026-07-05T04:04:04.138600+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.10216","citing_title":"Forget the Data and Fine-Tuning! Just Fold the Network to Compress","ref_index":84,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BH35MPFRTPTQD3GVGDJWGVAZZF","json":"https://pith.science/pith/BH35MPFRTPTQD3GVGDJWGVAZZF.json","graph_json":"https://pith.science/api/pith-number/BH35MPFRTPTQD3GVGDJWGVAZZF/graph.json","events_json":"https://pith.science/api/pith-number/BH35MPFRTPTQD3GVGDJWGVAZZF/events.json","paper":"https://pith.science/paper/BH35MPFR"},"agent_actions":{"view_html":"https://pith.science/pith/BH35MPFRTPTQD3GVGDJWGVAZZF","download_json":"https://pith.science/pith/BH35MPFRTPTQD3GVGDJWGVAZZF.json","view_paper":"https://pith.science/paper/BH35MPFR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.04595&json=true","fetch_graph":"https://pith.science/api/pith-number/BH35MPFRTPTQD3GVGDJWGVAZZF/graph.json","fetch_events":"https://pith.science/api/pith-number/BH35MPFRTPTQD3GVGDJWGVAZZF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BH35MPFRTPTQD3GVGDJWGVAZZF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BH35MPFRTPTQD3GVGDJWGVAZZF/action/storage_attestation","attest_author":"https://pith.science/pith/BH35MPFRTPTQD3GVGDJWGVAZZF/action/author_attestation","sign_citation":"https://pith.science/pith/BH35MPFRTPTQD3GVGDJWGVAZZF/action/citation_signature","submit_replication":"https://pith.science/pith/BH35MPFRTPTQD3GVGDJWGVAZZF/action/replication_record"}},"created_at":"2026-07-05T04:04:04.138600+00:00","updated_at":"2026-07-05T04:04:04.138600+00:00"}