{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:UT2PVTVMPSC6HLDZSGNO3ETNYW","short_pith_number":"pith:UT2PVTVM","schema_version":"1.0","canonical_sha256":"a4f4faceac7c85e3ac79919aed926dc59fc5ca7561651bc764c6f3909c30e9de","source":{"kind":"arxiv","id":"1805.11394","version":1},"attestation_state":"computed","paper":{"title":"A novel channel pruning method for deep neural network compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Jianquan Li, Qingyi Gu, Siyang Sun, Xingang Wang, Yiming Hu","submitted_at":"2018-05-29T12:37:46Z","abstract_excerpt":"In recent years, deep neural networks have achieved great success in the field of computer vision. However, it is still a big challenge to deploy these deep models on resource-constrained embedded devices such as mobile robots, smart phones and so on. Therefore, network compression for such platforms is a reasonable solution to reduce memory consumption and computation complexity. In this paper, a novel channel pruning method based on genetic algorithm is proposed to compress very deep Convolution Neural Networks (CNNs). Firstly, a pre-trained CNN model is pruned layer by layer according to th"},"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":"1805.11394","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-29T12:37:46Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"2f7ebec9b33100bc2b607ef21899006c69440a8672d2f07707642f52150be5cc","abstract_canon_sha256":"8fe6e85cf8090bba7b78709fd3f6717090e90c9b8803e2ca07888434e4a3fb77"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:42.724746Z","signature_b64":"t+uGQOrr6oSpn0JnM530Hw8BeQMQlRU14b3NJlmCmfOfjr/RJbWg87FOn8gU8Acehq2lP6bjs+/C+BQtlgwvDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4f4faceac7c85e3ac79919aed926dc59fc5ca7561651bc764c6f3909c30e9de","last_reissued_at":"2026-05-18T00:14:42.724096Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:42.724096Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A novel channel pruning method for deep neural network compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Jianquan Li, Qingyi Gu, Siyang Sun, Xingang Wang, Yiming Hu","submitted_at":"2018-05-29T12:37:46Z","abstract_excerpt":"In recent years, deep neural networks have achieved great success in the field of computer vision. However, it is still a big challenge to deploy these deep models on resource-constrained embedded devices such as mobile robots, smart phones and so on. Therefore, network compression for such platforms is a reasonable solution to reduce memory consumption and computation complexity. In this paper, a novel channel pruning method based on genetic algorithm is proposed to compress very deep Convolution Neural Networks (CNNs). Firstly, a pre-trained CNN model is pruned layer by layer according to th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.11394","kind":"arxiv","version":1},"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":"1805.11394","created_at":"2026-05-18T00:14:42.724211+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.11394v1","created_at":"2026-05-18T00:14:42.724211+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.11394","created_at":"2026-05-18T00:14:42.724211+00:00"},{"alias_kind":"pith_short_12","alias_value":"UT2PVTVMPSC6","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_16","alias_value":"UT2PVTVMPSC6HLDZ","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_8","alias_value":"UT2PVTVM","created_at":"2026-05-18T12:32:56.356000+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/UT2PVTVMPSC6HLDZSGNO3ETNYW","json":"https://pith.science/pith/UT2PVTVMPSC6HLDZSGNO3ETNYW.json","graph_json":"https://pith.science/api/pith-number/UT2PVTVMPSC6HLDZSGNO3ETNYW/graph.json","events_json":"https://pith.science/api/pith-number/UT2PVTVMPSC6HLDZSGNO3ETNYW/events.json","paper":"https://pith.science/paper/UT2PVTVM"},"agent_actions":{"view_html":"https://pith.science/pith/UT2PVTVMPSC6HLDZSGNO3ETNYW","download_json":"https://pith.science/pith/UT2PVTVMPSC6HLDZSGNO3ETNYW.json","view_paper":"https://pith.science/paper/UT2PVTVM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.11394&json=true","fetch_graph":"https://pith.science/api/pith-number/UT2PVTVMPSC6HLDZSGNO3ETNYW/graph.json","fetch_events":"https://pith.science/api/pith-number/UT2PVTVMPSC6HLDZSGNO3ETNYW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UT2PVTVMPSC6HLDZSGNO3ETNYW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UT2PVTVMPSC6HLDZSGNO3ETNYW/action/storage_attestation","attest_author":"https://pith.science/pith/UT2PVTVMPSC6HLDZSGNO3ETNYW/action/author_attestation","sign_citation":"https://pith.science/pith/UT2PVTVMPSC6HLDZSGNO3ETNYW/action/citation_signature","submit_replication":"https://pith.science/pith/UT2PVTVMPSC6HLDZSGNO3ETNYW/action/replication_record"}},"created_at":"2026-05-18T00:14:42.724211+00:00","updated_at":"2026-05-18T00:14:42.724211+00:00"}