{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:7CGOFLTR7KBUOTMV73UNPAN6WC","short_pith_number":"pith:7CGOFLTR","schema_version":"1.0","canonical_sha256":"f88ce2ae71fa83474d95fee8d781beb086f7c5e1dc4355457889e9235dc758cc","source":{"kind":"arxiv","id":"1511.06744","version":3},"attestation_state":"computed","paper":{"title":"Training CNNs with Low-Rank Filters for Efficient Image Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CV","authors_text":"Antonio Criminisi, Duncan Robertson, Jamie Shotton, Roberto Cipolla, Yani Ioannou","submitted_at":"2015-11-20T20:14:28Z","abstract_excerpt":"We propose a new method for creating computationally efficient convolutional neural networks (CNNs) by using low-rank representations of convolutional filters. Rather than approximating filters in previously-trained networks with more efficient versions, we learn a set of small basis filters from scratch; during training, the network learns to combine these basis filters into more complex filters that are discriminative for image classification. To train such networks, a novel weight initialization scheme is used. This allows effective initialization of connection weights in convolutional laye"},"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":"1511.06744","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-11-20T20:14:28Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"13f8fa656a111bb4d2759806f4e8f4b61b5079f2fbe9e8bbb97acc486d069445","abstract_canon_sha256":"ef83a798fb6c237974626f08b05fdf4c2502802285a1936ac82fc0d11bf39396"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:56:21.331420Z","signature_b64":"Vcak3MUcZQnU6F0g0VQm9dEdKjRKu8lJ40ME+tz7BZl0igmC8W4gjMqg/GzwudbGjA/v38qh6LjSiDTBKLqhBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f88ce2ae71fa83474d95fee8d781beb086f7c5e1dc4355457889e9235dc758cc","last_reissued_at":"2026-05-18T00:56:21.330621Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:56:21.330621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training CNNs with Low-Rank Filters for Efficient Image Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CV","authors_text":"Antonio Criminisi, Duncan Robertson, Jamie Shotton, Roberto Cipolla, Yani Ioannou","submitted_at":"2015-11-20T20:14:28Z","abstract_excerpt":"We propose a new method for creating computationally efficient convolutional neural networks (CNNs) by using low-rank representations of convolutional filters. Rather than approximating filters in previously-trained networks with more efficient versions, we learn a set of small basis filters from scratch; during training, the network learns to combine these basis filters into more complex filters that are discriminative for image classification. To train such networks, a novel weight initialization scheme is used. This allows effective initialization of connection weights in convolutional laye"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.06744","kind":"arxiv","version":3},"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":"1511.06744","created_at":"2026-05-18T00:56:21.330762+00:00"},{"alias_kind":"arxiv_version","alias_value":"1511.06744v3","created_at":"2026-05-18T00:56:21.330762+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.06744","created_at":"2026-05-18T00:56:21.330762+00:00"},{"alias_kind":"pith_short_12","alias_value":"7CGOFLTR7KBU","created_at":"2026-05-18T12:29:07.941421+00:00"},{"alias_kind":"pith_short_16","alias_value":"7CGOFLTR7KBUOTMV","created_at":"2026-05-18T12:29:07.941421+00:00"},{"alias_kind":"pith_short_8","alias_value":"7CGOFLTR","created_at":"2026-05-18T12:29:07.941421+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2312.05821","citing_title":"ASVD: Activation-aware Singular Value Decomposition for Compressing Large Language Models","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2604.23375","citing_title":"Hierarchical Spatio-Channel Clustering for Efficient Model Compression in Medical Image Analysis","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7CGOFLTR7KBUOTMV73UNPAN6WC","json":"https://pith.science/pith/7CGOFLTR7KBUOTMV73UNPAN6WC.json","graph_json":"https://pith.science/api/pith-number/7CGOFLTR7KBUOTMV73UNPAN6WC/graph.json","events_json":"https://pith.science/api/pith-number/7CGOFLTR7KBUOTMV73UNPAN6WC/events.json","paper":"https://pith.science/paper/7CGOFLTR"},"agent_actions":{"view_html":"https://pith.science/pith/7CGOFLTR7KBUOTMV73UNPAN6WC","download_json":"https://pith.science/pith/7CGOFLTR7KBUOTMV73UNPAN6WC.json","view_paper":"https://pith.science/paper/7CGOFLTR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1511.06744&json=true","fetch_graph":"https://pith.science/api/pith-number/7CGOFLTR7KBUOTMV73UNPAN6WC/graph.json","fetch_events":"https://pith.science/api/pith-number/7CGOFLTR7KBUOTMV73UNPAN6WC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7CGOFLTR7KBUOTMV73UNPAN6WC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7CGOFLTR7KBUOTMV73UNPAN6WC/action/storage_attestation","attest_author":"https://pith.science/pith/7CGOFLTR7KBUOTMV73UNPAN6WC/action/author_attestation","sign_citation":"https://pith.science/pith/7CGOFLTR7KBUOTMV73UNPAN6WC/action/citation_signature","submit_replication":"https://pith.science/pith/7CGOFLTR7KBUOTMV73UNPAN6WC/action/replication_record"}},"created_at":"2026-05-18T00:56:21.330762+00:00","updated_at":"2026-05-18T00:56:21.330762+00:00"}