{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:RH6OWMYNNRUVCFZYGTFWZCSO27","short_pith_number":"pith:RH6OWMYN","schema_version":"1.0","canonical_sha256":"89fceb330d6c6951173834cb6c8a4ed7c182fa95605ed21fe3805afeee902aad","source":{"kind":"arxiv","id":"1909.08174","version":1},"attestation_state":"computed","paper":{"title":"Gate Decorator: Global Filter Pruning Method for Accelerating Deep Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Jinmian Ye, Kun Yan, Meng Ma, Ping Wang, Zhonghui You","submitted_at":"2019-09-18T02:28:56Z","abstract_excerpt":"Filter pruning is one of the most effective ways to accelerate and compress convolutional neural networks (CNNs). In this work, we propose a global filter pruning algorithm called Gate Decorator, which transforms a vanilla CNN module by multiplying its output by the channel-wise scaling factors, i.e. gate. When the scaling factor is set to zero, it is equivalent to removing the corresponding filter. We use Taylor expansion to estimate the change in the loss function caused by setting the scaling factor to zero and use the estimation for the global filter importance ranking. Then we prune the n"},"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":"1909.08174","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-09-18T02:28:56Z","cross_cats_sorted":["cs.LG","eess.IV"],"title_canon_sha256":"acb576e38407f5fec3f75934baf842ffec1fb3a7ad13f6679686bfe6da918fae","abstract_canon_sha256":"cfb6ce128031217fba88dca745176c77181ff5f669a4f31a0560129aa3e8918b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:05:27.955911Z","signature_b64":"xLAIKJ3FXNIY0xngC9qnQ0KHuf0EcZbDQTmaCr8izrMnG9B6KtYIkA1cXoj5Aeuyhklft3p3YkjHp/UYAvTAAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89fceb330d6c6951173834cb6c8a4ed7c182fa95605ed21fe3805afeee902aad","last_reissued_at":"2026-07-05T00:05:27.955489Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:05:27.955489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gate Decorator: Global Filter Pruning Method for Accelerating Deep Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Jinmian Ye, Kun Yan, Meng Ma, Ping Wang, Zhonghui You","submitted_at":"2019-09-18T02:28:56Z","abstract_excerpt":"Filter pruning is one of the most effective ways to accelerate and compress convolutional neural networks (CNNs). In this work, we propose a global filter pruning algorithm called Gate Decorator, which transforms a vanilla CNN module by multiplying its output by the channel-wise scaling factors, i.e. gate. When the scaling factor is set to zero, it is equivalent to removing the corresponding filter. We use Taylor expansion to estimate the change in the loss function caused by setting the scaling factor to zero and use the estimation for the global filter importance ranking. Then we prune the n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.08174","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1909.08174/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":"1909.08174","created_at":"2026-07-05T00:05:27.955544+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.08174v1","created_at":"2026-07-05T00:05:27.955544+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.08174","created_at":"2026-07-05T00:05:27.955544+00:00"},{"alias_kind":"pith_short_12","alias_value":"RH6OWMYNNRUV","created_at":"2026-07-05T00:05:27.955544+00:00"},{"alias_kind":"pith_short_16","alias_value":"RH6OWMYNNRUVCFZY","created_at":"2026-07-05T00:05:27.955544+00:00"},{"alias_kind":"pith_short_8","alias_value":"RH6OWMYN","created_at":"2026-07-05T00:05:27.955544+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.24380","citing_title":"Structural Pruning of Large Vision Language Models: A Comprehensive Study on Pruning Dynamics, Recovery, and Data Efficiency","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RH6OWMYNNRUVCFZYGTFWZCSO27","json":"https://pith.science/pith/RH6OWMYNNRUVCFZYGTFWZCSO27.json","graph_json":"https://pith.science/api/pith-number/RH6OWMYNNRUVCFZYGTFWZCSO27/graph.json","events_json":"https://pith.science/api/pith-number/RH6OWMYNNRUVCFZYGTFWZCSO27/events.json","paper":"https://pith.science/paper/RH6OWMYN"},"agent_actions":{"view_html":"https://pith.science/pith/RH6OWMYNNRUVCFZYGTFWZCSO27","download_json":"https://pith.science/pith/RH6OWMYNNRUVCFZYGTFWZCSO27.json","view_paper":"https://pith.science/paper/RH6OWMYN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.08174&json=true","fetch_graph":"https://pith.science/api/pith-number/RH6OWMYNNRUVCFZYGTFWZCSO27/graph.json","fetch_events":"https://pith.science/api/pith-number/RH6OWMYNNRUVCFZYGTFWZCSO27/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RH6OWMYNNRUVCFZYGTFWZCSO27/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RH6OWMYNNRUVCFZYGTFWZCSO27/action/storage_attestation","attest_author":"https://pith.science/pith/RH6OWMYNNRUVCFZYGTFWZCSO27/action/author_attestation","sign_citation":"https://pith.science/pith/RH6OWMYNNRUVCFZYGTFWZCSO27/action/citation_signature","submit_replication":"https://pith.science/pith/RH6OWMYNNRUVCFZYGTFWZCSO27/action/replication_record"}},"created_at":"2026-07-05T00:05:27.955544+00:00","updated_at":"2026-07-05T00:05:27.955544+00:00"}