{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:BO4U33EV32VUBMJVTMXYKKAE67","short_pith_number":"pith:BO4U33EV","schema_version":"1.0","canonical_sha256":"0bb94dec95deab40b1359b2f852804f7dabdc36334e6e15615f245c7f5fa6756","source":{"kind":"arxiv","id":"1708.06973","version":1},"attestation_state":"computed","paper":{"title":"Exploiting Convolution Filter Patterns for Transfer Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haz{\\i}m Kemal Ekenel, Mehmet Ayg\\\"un, Yusuf Aytar","submitted_at":"2017-08-23T12:13:30Z","abstract_excerpt":"In this paper, we introduce a new regularization technique for transfer learning. The aim of the proposed approach is to capture statistical relationships among convolution filters learned from a well-trained network and transfer this knowledge to another network. Since convolution filters of the prevalent deep Convolutional Neural Network (CNN) models share a number of similar patterns, in order to speed up the learning procedure, we capture such correlations by Gaussian Mixture Models (GMMs) and transfer them using a regularization term. We have conducted extensive experiments on the CIFAR10"},"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":"1708.06973","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-23T12:13:30Z","cross_cats_sorted":[],"title_canon_sha256":"6fb3765a55368e30be77de55073799bc9b746930d36f5d32d8f8041bbce60a6f","abstract_canon_sha256":"fd33b898762b5b2b02776cc6556688944b120fe672a380b05cd42173ac9a9e41"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:36:48.718145Z","signature_b64":"Kp9Er8QwC6kQMm6LQt4rgvHMs8u29S8m+BAuU3IYZsWjzZSCrINWbtDqwWlxgKWrNfHBjkt4dXFBCeZ76L2hCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0bb94dec95deab40b1359b2f852804f7dabdc36334e6e15615f245c7f5fa6756","last_reissued_at":"2026-05-18T00:36:48.717713Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:36:48.717713Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploiting Convolution Filter Patterns for Transfer Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haz{\\i}m Kemal Ekenel, Mehmet Ayg\\\"un, Yusuf Aytar","submitted_at":"2017-08-23T12:13:30Z","abstract_excerpt":"In this paper, we introduce a new regularization technique for transfer learning. The aim of the proposed approach is to capture statistical relationships among convolution filters learned from a well-trained network and transfer this knowledge to another network. Since convolution filters of the prevalent deep Convolutional Neural Network (CNN) models share a number of similar patterns, in order to speed up the learning procedure, we capture such correlations by Gaussian Mixture Models (GMMs) and transfer them using a regularization term. We have conducted extensive experiments on the CIFAR10"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.06973","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":"1708.06973","created_at":"2026-05-18T00:36:48.717778+00:00"},{"alias_kind":"arxiv_version","alias_value":"1708.06973v1","created_at":"2026-05-18T00:36:48.717778+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.06973","created_at":"2026-05-18T00:36:48.717778+00:00"},{"alias_kind":"pith_short_12","alias_value":"BO4U33EV32VU","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_16","alias_value":"BO4U33EV32VUBMJV","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_8","alias_value":"BO4U33EV","created_at":"2026-05-18T12:31:08.081275+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/BO4U33EV32VUBMJVTMXYKKAE67","json":"https://pith.science/pith/BO4U33EV32VUBMJVTMXYKKAE67.json","graph_json":"https://pith.science/api/pith-number/BO4U33EV32VUBMJVTMXYKKAE67/graph.json","events_json":"https://pith.science/api/pith-number/BO4U33EV32VUBMJVTMXYKKAE67/events.json","paper":"https://pith.science/paper/BO4U33EV"},"agent_actions":{"view_html":"https://pith.science/pith/BO4U33EV32VUBMJVTMXYKKAE67","download_json":"https://pith.science/pith/BO4U33EV32VUBMJVTMXYKKAE67.json","view_paper":"https://pith.science/paper/BO4U33EV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1708.06973&json=true","fetch_graph":"https://pith.science/api/pith-number/BO4U33EV32VUBMJVTMXYKKAE67/graph.json","fetch_events":"https://pith.science/api/pith-number/BO4U33EV32VUBMJVTMXYKKAE67/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BO4U33EV32VUBMJVTMXYKKAE67/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BO4U33EV32VUBMJVTMXYKKAE67/action/storage_attestation","attest_author":"https://pith.science/pith/BO4U33EV32VUBMJVTMXYKKAE67/action/author_attestation","sign_citation":"https://pith.science/pith/BO4U33EV32VUBMJVTMXYKKAE67/action/citation_signature","submit_replication":"https://pith.science/pith/BO4U33EV32VUBMJVTMXYKKAE67/action/replication_record"}},"created_at":"2026-05-18T00:36:48.717778+00:00","updated_at":"2026-05-18T00:36:48.717778+00:00"}