{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:7OES2TMULDEFL3KHSGOKKNDB5J","short_pith_number":"pith:7OES2TMU","schema_version":"1.0","canonical_sha256":"fb892d4d9458c855ed47919ca53461ea435561951bedf7ae6043d5cc2ce0fa28","source":{"kind":"arxiv","id":"1807.11254","version":2},"attestation_state":"computed","paper":{"title":"Extreme Network Compression via Filter Group Approximation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Peng, Di Xie, Shiliang Pu, Shun Zhang, Wenming Tan, Zheyang Li","submitted_at":"2018-07-30T09:42:05Z","abstract_excerpt":"In this paper we propose a novel decomposition method based on filter group approximation, which can significantly reduce the redundancy of deep convolutional neural networks (CNNs) while maintaining the majority of feature representation. Unlike other low-rank decomposition algorithms which operate on spatial or channel dimension of filters, our proposed method mainly focuses on exploiting the filter group structure for each layer. For several commonly used CNN models, including VGG and ResNet, our method can reduce over 80% floating-point operations (FLOPs) with less accuracy drop than state"},"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":"1807.11254","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-30T09:42:05Z","cross_cats_sorted":[],"title_canon_sha256":"67fe328c1c18a028772838de81cce3bd9f6d8164f2cbc7f8ef11b1586bdfc75b","abstract_canon_sha256":"932d7640be14de1b9fe6d3e092854168dbb047aae07a857c41f89a4db89a831c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:09:23.739763Z","signature_b64":"W5UXPMpBlJa/r9ucGDh35ByjeXqNOSzYI9+OwevQyM4R5rSzADcRL/ol6PDwMhEmtR7otg8vQPY0rgb3UiV1Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb892d4d9458c855ed47919ca53461ea435561951bedf7ae6043d5cc2ce0fa28","last_reissued_at":"2026-05-18T00:09:23.739222Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:09:23.739222Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Extreme Network Compression via Filter Group Approximation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Peng, Di Xie, Shiliang Pu, Shun Zhang, Wenming Tan, Zheyang Li","submitted_at":"2018-07-30T09:42:05Z","abstract_excerpt":"In this paper we propose a novel decomposition method based on filter group approximation, which can significantly reduce the redundancy of deep convolutional neural networks (CNNs) while maintaining the majority of feature representation. Unlike other low-rank decomposition algorithms which operate on spatial or channel dimension of filters, our proposed method mainly focuses on exploiting the filter group structure for each layer. For several commonly used CNN models, including VGG and ResNet, our method can reduce over 80% floating-point operations (FLOPs) with less accuracy drop than state"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.11254","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":""},"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":"1807.11254","created_at":"2026-05-18T00:09:23.739295+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.11254v2","created_at":"2026-05-18T00:09:23.739295+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.11254","created_at":"2026-05-18T00:09:23.739295+00:00"},{"alias_kind":"pith_short_12","alias_value":"7OES2TMULDEF","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_16","alias_value":"7OES2TMULDEFL3KH","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_8","alias_value":"7OES2TMU","created_at":"2026-05-18T12:32:11.075285+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/7OES2TMULDEFL3KHSGOKKNDB5J","json":"https://pith.science/pith/7OES2TMULDEFL3KHSGOKKNDB5J.json","graph_json":"https://pith.science/api/pith-number/7OES2TMULDEFL3KHSGOKKNDB5J/graph.json","events_json":"https://pith.science/api/pith-number/7OES2TMULDEFL3KHSGOKKNDB5J/events.json","paper":"https://pith.science/paper/7OES2TMU"},"agent_actions":{"view_html":"https://pith.science/pith/7OES2TMULDEFL3KHSGOKKNDB5J","download_json":"https://pith.science/pith/7OES2TMULDEFL3KHSGOKKNDB5J.json","view_paper":"https://pith.science/paper/7OES2TMU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.11254&json=true","fetch_graph":"https://pith.science/api/pith-number/7OES2TMULDEFL3KHSGOKKNDB5J/graph.json","fetch_events":"https://pith.science/api/pith-number/7OES2TMULDEFL3KHSGOKKNDB5J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7OES2TMULDEFL3KHSGOKKNDB5J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7OES2TMULDEFL3KHSGOKKNDB5J/action/storage_attestation","attest_author":"https://pith.science/pith/7OES2TMULDEFL3KHSGOKKNDB5J/action/author_attestation","sign_citation":"https://pith.science/pith/7OES2TMULDEFL3KHSGOKKNDB5J/action/citation_signature","submit_replication":"https://pith.science/pith/7OES2TMULDEFL3KHSGOKKNDB5J/action/replication_record"}},"created_at":"2026-05-18T00:09:23.739295+00:00","updated_at":"2026-05-18T00:09:23.739295+00:00"}