{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:XRD5E5MCSF2LCETCAWMCEPBMZO","short_pith_number":"pith:XRD5E5MC","schema_version":"1.0","canonical_sha256":"bc47d275829174b112620598223c2ccbae31b01c48fd1ead0693fe2de70a0b7c","source":{"kind":"arxiv","id":"1803.05729","version":1},"attestation_state":"computed","paper":{"title":"Exploring Linear Relationship in Feature Map Subspace for ConvNets Compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dong Wang, Jun Zhou, Lei Zhou, Xiao Bai, Xueni Zhang","submitted_at":"2018-03-15T13:20:16Z","abstract_excerpt":"While the research on convolutional neural networks (CNNs) is progressing quickly, the real-world deployment of these models is often limited by computing resources and memory constraints. In this paper, we address this issue by proposing a novel filter pruning method to compress and accelerate CNNs. Our work is based on the linear relationship identified in different feature map subspaces via visualization of feature maps. Such linear relationship implies that the information in CNNs is redundant. Our method eliminates the redundancy in convolutional filters by applying subspace clustering to"},"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":"1803.05729","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-15T13:20:16Z","cross_cats_sorted":[],"title_canon_sha256":"1cf2c89b4f13549c9e76ef07864809b7d1137d9221eebf2b41c601a2d06e5d2b","abstract_canon_sha256":"3efe480e4a54a7a3bc6bcbc679fff1c2ea17b75e4b7351a1fb0e65605447290d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:54.800353Z","signature_b64":"404998x+hPCXDiwTAY9zdl7zYNot5gWMj/tOcV9zIWN3S8NPh66wrnyE5dCw9b3SphFWUZ+tQfW20sHqUrkmBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc47d275829174b112620598223c2ccbae31b01c48fd1ead0693fe2de70a0b7c","last_reissued_at":"2026-05-18T00:20:54.799767Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:54.799767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Linear Relationship in Feature Map Subspace for ConvNets Compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dong Wang, Jun Zhou, Lei Zhou, Xiao Bai, Xueni Zhang","submitted_at":"2018-03-15T13:20:16Z","abstract_excerpt":"While the research on convolutional neural networks (CNNs) is progressing quickly, the real-world deployment of these models is often limited by computing resources and memory constraints. In this paper, we address this issue by proposing a novel filter pruning method to compress and accelerate CNNs. Our work is based on the linear relationship identified in different feature map subspaces via visualization of feature maps. Such linear relationship implies that the information in CNNs is redundant. Our method eliminates the redundancy in convolutional filters by applying subspace clustering to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.05729","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":"1803.05729","created_at":"2026-05-18T00:20:54.799860+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.05729v1","created_at":"2026-05-18T00:20:54.799860+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.05729","created_at":"2026-05-18T00:20:54.799860+00:00"},{"alias_kind":"pith_short_12","alias_value":"XRD5E5MCSF2L","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_16","alias_value":"XRD5E5MCSF2LCETC","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_8","alias_value":"XRD5E5MC","created_at":"2026-05-18T12:33:01.666342+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.23375","citing_title":"Hierarchical Spatio-Channel Clustering for Efficient Model Compression in Medical Image Analysis","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XRD5E5MCSF2LCETCAWMCEPBMZO","json":"https://pith.science/pith/XRD5E5MCSF2LCETCAWMCEPBMZO.json","graph_json":"https://pith.science/api/pith-number/XRD5E5MCSF2LCETCAWMCEPBMZO/graph.json","events_json":"https://pith.science/api/pith-number/XRD5E5MCSF2LCETCAWMCEPBMZO/events.json","paper":"https://pith.science/paper/XRD5E5MC"},"agent_actions":{"view_html":"https://pith.science/pith/XRD5E5MCSF2LCETCAWMCEPBMZO","download_json":"https://pith.science/pith/XRD5E5MCSF2LCETCAWMCEPBMZO.json","view_paper":"https://pith.science/paper/XRD5E5MC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.05729&json=true","fetch_graph":"https://pith.science/api/pith-number/XRD5E5MCSF2LCETCAWMCEPBMZO/graph.json","fetch_events":"https://pith.science/api/pith-number/XRD5E5MCSF2LCETCAWMCEPBMZO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XRD5E5MCSF2LCETCAWMCEPBMZO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XRD5E5MCSF2LCETCAWMCEPBMZO/action/storage_attestation","attest_author":"https://pith.science/pith/XRD5E5MCSF2LCETCAWMCEPBMZO/action/author_attestation","sign_citation":"https://pith.science/pith/XRD5E5MCSF2LCETCAWMCEPBMZO/action/citation_signature","submit_replication":"https://pith.science/pith/XRD5E5MCSF2LCETCAWMCEPBMZO/action/replication_record"}},"created_at":"2026-05-18T00:20:54.799860+00:00","updated_at":"2026-05-18T00:20:54.799860+00:00"}