{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:WMIIN3X2FAMGUKC2MC2DFN7FHJ","short_pith_number":"pith:WMIIN3X2","schema_version":"1.0","canonical_sha256":"b31086eefa28186a285a60b432b7e53a7c9bba8238a84ca259d6166ca98ebaea","source":{"kind":"arxiv","id":"1605.09673","version":2},"attestation_state":"computed","paper":{"title":"Dynamic Filter Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Bert De Brabandere, Luc Van Gool, Tinne Tuytelaars, Xu Jia","submitted_at":"2016-05-31T15:29:36Z","abstract_excerpt":"In a traditional convolutional layer, the learned filters stay fixed after training. In contrast, we introduce a new framework, the Dynamic Filter Network, where filters are generated dynamically conditioned on an input. We show that this architecture is a powerful one, with increased flexibility thanks to its adaptive nature, yet without an excessive increase in the number of model parameters. A wide variety of filtering operations can be learned this way, including local spatial transformations, but also others like selective (de)blurring or adaptive feature extraction. Moreover, multiple su"},"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":"1605.09673","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-31T15:29:36Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"6cb28ac95f3a0d4b060530b2eaec2a458b9622304393b33a85c224b21504822d","abstract_canon_sha256":"073e3a9eb7bcd87fb6abbacc32230bc915b83557b08c54f07880a4df89adda8c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:12:54.564341Z","signature_b64":"3VwXOuC4Q3bw/X+f+MR4oRVUyiAeeP5DcCSCXVgVh61NTl4BIKgNdsVUtSgpm60v3F9jMSYe1FqccYks7fe1Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b31086eefa28186a285a60b432b7e53a7c9bba8238a84ca259d6166ca98ebaea","last_reissued_at":"2026-05-18T01:12:54.563951Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:12:54.563951Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dynamic Filter Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Bert De Brabandere, Luc Van Gool, Tinne Tuytelaars, Xu Jia","submitted_at":"2016-05-31T15:29:36Z","abstract_excerpt":"In a traditional convolutional layer, the learned filters stay fixed after training. In contrast, we introduce a new framework, the Dynamic Filter Network, where filters are generated dynamically conditioned on an input. We show that this architecture is a powerful one, with increased flexibility thanks to its adaptive nature, yet without an excessive increase in the number of model parameters. A wide variety of filtering operations can be learned this way, including local spatial transformations, but also others like selective (de)blurring or adaptive feature extraction. Moreover, multiple su"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.09673","kind":"arxiv","version":2},"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":"1605.09673","created_at":"2026-05-18T01:12:54.564007+00:00"},{"alias_kind":"arxiv_version","alias_value":"1605.09673v2","created_at":"2026-05-18T01:12:54.564007+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.09673","created_at":"2026-05-18T01:12:54.564007+00:00"},{"alias_kind":"pith_short_12","alias_value":"WMIIN3X2FAMG","created_at":"2026-05-18T12:30:48.956258+00:00"},{"alias_kind":"pith_short_16","alias_value":"WMIIN3X2FAMGUKC2","created_at":"2026-05-18T12:30:48.956258+00:00"},{"alias_kind":"pith_short_8","alias_value":"WMIIN3X2","created_at":"2026-05-18T12:30:48.956258+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2510.09806","citing_title":"AMIGO: a Data-Driven Calibration of the JWST Interferometer","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06127","citing_title":"Continuous Expert Assembly: Instance-Conditioned Low-Rank Residuals for All-in-One Image Restoration","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WMIIN3X2FAMGUKC2MC2DFN7FHJ","json":"https://pith.science/pith/WMIIN3X2FAMGUKC2MC2DFN7FHJ.json","graph_json":"https://pith.science/api/pith-number/WMIIN3X2FAMGUKC2MC2DFN7FHJ/graph.json","events_json":"https://pith.science/api/pith-number/WMIIN3X2FAMGUKC2MC2DFN7FHJ/events.json","paper":"https://pith.science/paper/WMIIN3X2"},"agent_actions":{"view_html":"https://pith.science/pith/WMIIN3X2FAMGUKC2MC2DFN7FHJ","download_json":"https://pith.science/pith/WMIIN3X2FAMGUKC2MC2DFN7FHJ.json","view_paper":"https://pith.science/paper/WMIIN3X2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1605.09673&json=true","fetch_graph":"https://pith.science/api/pith-number/WMIIN3X2FAMGUKC2MC2DFN7FHJ/graph.json","fetch_events":"https://pith.science/api/pith-number/WMIIN3X2FAMGUKC2MC2DFN7FHJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WMIIN3X2FAMGUKC2MC2DFN7FHJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WMIIN3X2FAMGUKC2MC2DFN7FHJ/action/storage_attestation","attest_author":"https://pith.science/pith/WMIIN3X2FAMGUKC2MC2DFN7FHJ/action/author_attestation","sign_citation":"https://pith.science/pith/WMIIN3X2FAMGUKC2MC2DFN7FHJ/action/citation_signature","submit_replication":"https://pith.science/pith/WMIIN3X2FAMGUKC2MC2DFN7FHJ/action/replication_record"}},"created_at":"2026-05-18T01:12:54.564007+00:00","updated_at":"2026-05-18T01:12:54.564007+00:00"}