{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:JAC42DFWT5W75A5ZZAB74W37M5","short_pith_number":"pith:JAC42DFW","schema_version":"1.0","canonical_sha256":"4805cd0cb69f6dfe83b9c803fe5b7f6750e37a5b2b7282a1e732744623563e85","source":{"kind":"arxiv","id":"1910.09455","version":3},"attestation_state":"computed","paper":{"title":"Depth-wise Decomposition for Accelerating Separable Convolutions in Efficient Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cindy X. Le, Congrui Hetang, Jianing Qian, Jianren Wang, Qi Lyu, Tianwei Yue, Wenping Wang, Yihui He","submitted_at":"2019-10-21T15:37:53Z","abstract_excerpt":"Very deep convolutional neural networks (CNNs) have been firmly established as the primary methods for many computer vision tasks. However, most state-of-the-art CNNs are large, which results in high inference latency. Recently, depth-wise separable convolution has been proposed for image recognition tasks on computationally limited platforms such as robotics and self-driving cars. Though it is much faster than its counterpart, regular convolution, accuracy is sacrificed. In this paper, we propose a novel decomposition approach based on SVD, namely depth-wise decomposition, for expanding regul"},"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":"1910.09455","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-10-21T15:37:53Z","cross_cats_sorted":[],"title_canon_sha256":"fc1925158798bd24f023ee8214e8c414cab1fd1fc43edecfebda412a0e324b19","abstract_canon_sha256":"15ab4a68e4aae50fc0e16718136cfaba017ede598bb0ddcc0ef91f3f328c2a52"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:56:44.480944Z","signature_b64":"ePKCRhBDotd7Qu6cxtBFArA3puYLHjLjzGSxXQuEnRfCN7fKHwzAYvrfcxtnS0FeI8Wp6MftCOjOw/poJwrICw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4805cd0cb69f6dfe83b9c803fe5b7f6750e37a5b2b7282a1e732744623563e85","last_reissued_at":"2026-07-05T09:56:44.480479Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:56:44.480479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Depth-wise Decomposition for Accelerating Separable Convolutions in Efficient Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cindy X. Le, Congrui Hetang, Jianing Qian, Jianren Wang, Qi Lyu, Tianwei Yue, Wenping Wang, Yihui He","submitted_at":"2019-10-21T15:37:53Z","abstract_excerpt":"Very deep convolutional neural networks (CNNs) have been firmly established as the primary methods for many computer vision tasks. However, most state-of-the-art CNNs are large, which results in high inference latency. Recently, depth-wise separable convolution has been proposed for image recognition tasks on computationally limited platforms such as robotics and self-driving cars. Though it is much faster than its counterpart, regular convolution, accuracy is sacrificed. In this paper, we propose a novel decomposition approach based on SVD, namely depth-wise decomposition, for expanding regul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.09455","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1910.09455/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":"1910.09455","created_at":"2026-07-05T09:56:44.480532+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.09455v3","created_at":"2026-07-05T09:56:44.480532+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.09455","created_at":"2026-07-05T09:56:44.480532+00:00"},{"alias_kind":"pith_short_12","alias_value":"JAC42DFWT5W7","created_at":"2026-07-05T09:56:44.480532+00:00"},{"alias_kind":"pith_short_16","alias_value":"JAC42DFWT5W75A5Z","created_at":"2026-07-05T09:56:44.480532+00:00"},{"alias_kind":"pith_short_8","alias_value":"JAC42DFW","created_at":"2026-07-05T09:56:44.480532+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/JAC42DFWT5W75A5ZZAB74W37M5","json":"https://pith.science/pith/JAC42DFWT5W75A5ZZAB74W37M5.json","graph_json":"https://pith.science/api/pith-number/JAC42DFWT5W75A5ZZAB74W37M5/graph.json","events_json":"https://pith.science/api/pith-number/JAC42DFWT5W75A5ZZAB74W37M5/events.json","paper":"https://pith.science/paper/JAC42DFW"},"agent_actions":{"view_html":"https://pith.science/pith/JAC42DFWT5W75A5ZZAB74W37M5","download_json":"https://pith.science/pith/JAC42DFWT5W75A5ZZAB74W37M5.json","view_paper":"https://pith.science/paper/JAC42DFW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.09455&json=true","fetch_graph":"https://pith.science/api/pith-number/JAC42DFWT5W75A5ZZAB74W37M5/graph.json","fetch_events":"https://pith.science/api/pith-number/JAC42DFWT5W75A5ZZAB74W37M5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JAC42DFWT5W75A5ZZAB74W37M5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JAC42DFWT5W75A5ZZAB74W37M5/action/storage_attestation","attest_author":"https://pith.science/pith/JAC42DFWT5W75A5ZZAB74W37M5/action/author_attestation","sign_citation":"https://pith.science/pith/JAC42DFWT5W75A5ZZAB74W37M5/action/citation_signature","submit_replication":"https://pith.science/pith/JAC42DFWT5W75A5ZZAB74W37M5/action/replication_record"}},"created_at":"2026-07-05T09:56:44.480532+00:00","updated_at":"2026-07-05T09:56:44.480532+00:00"}