{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:SBA7VIQYIWUJJDM7P7TAXOMNZT","short_pith_number":"pith:SBA7VIQY","schema_version":"1.0","canonical_sha256":"9041faa21845a8948d9f7fe60bb98dccf5ce8ce207457cb35b3293c2b77884d9","source":{"kind":"arxiv","id":"1711.11473","version":2},"attestation_state":"computed","paper":{"title":"Spatially-Adaptive Filter Units for Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ale\\v{s} Leonardis, Domen Tabernik, Matej Kristan","submitted_at":"2017-11-30T15:49:13Z","abstract_excerpt":"Classical deep convolutional networks increase receptive field size by either gradual resolution reduction or application of hand-crafted dilated convolutions to prevent increase in the number of parameters. In this paper we propose a novel displaced aggregation unit (DAU) that does not require hand-crafting. In contrast to classical filters with units (pixels) placed on a fixed regular grid, the displacement of the DAUs are learned, which enables filters to spatially-adapt their receptive field to a given problem. We extensively demonstrate the strength of DAUs on a classification and semanti"},"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":"1711.11473","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-30T15:49:13Z","cross_cats_sorted":[],"title_canon_sha256":"f5f1a1a0ce81d6b630d965b66154cb055f4ced49fbf91113e2c3fe799d845b26","abstract_canon_sha256":"1a46443afe7b63b20b89323a18813318249a6dcb7f44e5f8dcfec8bf5f7af8e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:55.900002Z","signature_b64":"4vc/ZJ60CFuTsDScCEeRdjzCnN5E1ESCZPCg9lqJkRJFveRRnbs4Q9qifdXJtN7mkL5uMm+7QUyn+7+qanZkDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9041faa21845a8948d9f7fe60bb98dccf5ce8ce207457cb35b3293c2b77884d9","last_reissued_at":"2026-05-18T00:20:55.899392Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:55.899392Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spatially-Adaptive Filter Units for Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ale\\v{s} Leonardis, Domen Tabernik, Matej Kristan","submitted_at":"2017-11-30T15:49:13Z","abstract_excerpt":"Classical deep convolutional networks increase receptive field size by either gradual resolution reduction or application of hand-crafted dilated convolutions to prevent increase in the number of parameters. In this paper we propose a novel displaced aggregation unit (DAU) that does not require hand-crafting. In contrast to classical filters with units (pixels) placed on a fixed regular grid, the displacement of the DAUs are learned, which enables filters to spatially-adapt their receptive field to a given problem. We extensively demonstrate the strength of DAUs on a classification and semanti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.11473","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":"1711.11473","created_at":"2026-05-18T00:20:55.899485+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.11473v2","created_at":"2026-05-18T00:20:55.899485+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.11473","created_at":"2026-05-18T00:20:55.899485+00:00"},{"alias_kind":"pith_short_12","alias_value":"SBA7VIQYIWUJ","created_at":"2026-05-18T12:31:43.269735+00:00"},{"alias_kind":"pith_short_16","alias_value":"SBA7VIQYIWUJJDM7","created_at":"2026-05-18T12:31:43.269735+00:00"},{"alias_kind":"pith_short_8","alias_value":"SBA7VIQY","created_at":"2026-05-18T12:31:43.269735+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/SBA7VIQYIWUJJDM7P7TAXOMNZT","json":"https://pith.science/pith/SBA7VIQYIWUJJDM7P7TAXOMNZT.json","graph_json":"https://pith.science/api/pith-number/SBA7VIQYIWUJJDM7P7TAXOMNZT/graph.json","events_json":"https://pith.science/api/pith-number/SBA7VIQYIWUJJDM7P7TAXOMNZT/events.json","paper":"https://pith.science/paper/SBA7VIQY"},"agent_actions":{"view_html":"https://pith.science/pith/SBA7VIQYIWUJJDM7P7TAXOMNZT","download_json":"https://pith.science/pith/SBA7VIQYIWUJJDM7P7TAXOMNZT.json","view_paper":"https://pith.science/paper/SBA7VIQY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.11473&json=true","fetch_graph":"https://pith.science/api/pith-number/SBA7VIQYIWUJJDM7P7TAXOMNZT/graph.json","fetch_events":"https://pith.science/api/pith-number/SBA7VIQYIWUJJDM7P7TAXOMNZT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SBA7VIQYIWUJJDM7P7TAXOMNZT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SBA7VIQYIWUJJDM7P7TAXOMNZT/action/storage_attestation","attest_author":"https://pith.science/pith/SBA7VIQYIWUJJDM7P7TAXOMNZT/action/author_attestation","sign_citation":"https://pith.science/pith/SBA7VIQYIWUJJDM7P7TAXOMNZT/action/citation_signature","submit_replication":"https://pith.science/pith/SBA7VIQYIWUJJDM7P7TAXOMNZT/action/replication_record"}},"created_at":"2026-05-18T00:20:55.899485+00:00","updated_at":"2026-05-18T00:20:55.899485+00:00"}