{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:U6YXHIRTKLCRTIJ5MBWPYOHZTY","short_pith_number":"pith:U6YXHIRT","schema_version":"1.0","canonical_sha256":"a7b173a23352c519a13d606cfc38f99e217502f97f61940c2f39e628cfac444d","source":{"kind":"arxiv","id":"2307.00198","version":1},"attestation_state":"computed","paper":{"title":"Filter Pruning for Efficient CNNs via Knowledge-driven Differential Filter Sampler","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baochang Zhang, David Doermann, Jiao Xie, Jungong Han, Shaohui Lin, Wenxuan Huang, Yunhang Shen, Zhou Yu","submitted_at":"2023-07-01T02:28:41Z","abstract_excerpt":"Filter pruning simultaneously accelerates the computation and reduces the memory overhead of CNNs, which can be effectively applied to edge devices and cloud services. In this paper, we propose a novel Knowledge-driven Differential Filter Sampler~(KDFS) with Masked Filter Modeling~(MFM) framework for filter pruning, which globally prunes the redundant filters based on the prior knowledge of a pre-trained model in a differential and non-alternative optimization. Specifically, we design a differential sampler with learnable sampling parameters to build a binary mask vector for each layer, determ"},"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":"2307.00198","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-01T02:28:41Z","cross_cats_sorted":[],"title_canon_sha256":"d0e2814de9fd5bdb61548d73002570c525c921bd81481068344680f410e14dc6","abstract_canon_sha256":"fe75e26800c56350734932b9643298153af3665170d184646408b2fa744aaf36"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:26:52.946671Z","signature_b64":"3F4YRSKHhL/HgnO7dOGMuQ0Mp3lNn3xuG8h4GI0T9eeTs5Oea+xvl1xkJprWuYCoihSvr1tT13Q6XHyOjZyWBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7b173a23352c519a13d606cfc38f99e217502f97f61940c2f39e628cfac444d","last_reissued_at":"2026-07-05T06:26:52.946176Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:26:52.946176Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Filter Pruning for Efficient CNNs via Knowledge-driven Differential Filter Sampler","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baochang Zhang, David Doermann, Jiao Xie, Jungong Han, Shaohui Lin, Wenxuan Huang, Yunhang Shen, Zhou Yu","submitted_at":"2023-07-01T02:28:41Z","abstract_excerpt":"Filter pruning simultaneously accelerates the computation and reduces the memory overhead of CNNs, which can be effectively applied to edge devices and cloud services. In this paper, we propose a novel Knowledge-driven Differential Filter Sampler~(KDFS) with Masked Filter Modeling~(MFM) framework for filter pruning, which globally prunes the redundant filters based on the prior knowledge of a pre-trained model in a differential and non-alternative optimization. Specifically, we design a differential sampler with learnable sampling parameters to build a binary mask vector for each layer, determ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.00198","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/2307.00198/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":"2307.00198","created_at":"2026-07-05T06:26:52.946232+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.00198v1","created_at":"2026-07-05T06:26:52.946232+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.00198","created_at":"2026-07-05T06:26:52.946232+00:00"},{"alias_kind":"pith_short_12","alias_value":"U6YXHIRTKLCR","created_at":"2026-07-05T06:26:52.946232+00:00"},{"alias_kind":"pith_short_16","alias_value":"U6YXHIRTKLCRTIJ5","created_at":"2026-07-05T06:26:52.946232+00:00"},{"alias_kind":"pith_short_8","alias_value":"U6YXHIRT","created_at":"2026-07-05T06:26:52.946232+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/U6YXHIRTKLCRTIJ5MBWPYOHZTY","json":"https://pith.science/pith/U6YXHIRTKLCRTIJ5MBWPYOHZTY.json","graph_json":"https://pith.science/api/pith-number/U6YXHIRTKLCRTIJ5MBWPYOHZTY/graph.json","events_json":"https://pith.science/api/pith-number/U6YXHIRTKLCRTIJ5MBWPYOHZTY/events.json","paper":"https://pith.science/paper/U6YXHIRT"},"agent_actions":{"view_html":"https://pith.science/pith/U6YXHIRTKLCRTIJ5MBWPYOHZTY","download_json":"https://pith.science/pith/U6YXHIRTKLCRTIJ5MBWPYOHZTY.json","view_paper":"https://pith.science/paper/U6YXHIRT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.00198&json=true","fetch_graph":"https://pith.science/api/pith-number/U6YXHIRTKLCRTIJ5MBWPYOHZTY/graph.json","fetch_events":"https://pith.science/api/pith-number/U6YXHIRTKLCRTIJ5MBWPYOHZTY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U6YXHIRTKLCRTIJ5MBWPYOHZTY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U6YXHIRTKLCRTIJ5MBWPYOHZTY/action/storage_attestation","attest_author":"https://pith.science/pith/U6YXHIRTKLCRTIJ5MBWPYOHZTY/action/author_attestation","sign_citation":"https://pith.science/pith/U6YXHIRTKLCRTIJ5MBWPYOHZTY/action/citation_signature","submit_replication":"https://pith.science/pith/U6YXHIRTKLCRTIJ5MBWPYOHZTY/action/replication_record"}},"created_at":"2026-07-05T06:26:52.946232+00:00","updated_at":"2026-07-05T06:26:52.946232+00:00"}