{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:BFJBCPMZMNHH75HLPLR5ZYEFY6","short_pith_number":"pith:BFJBCPMZ","schema_version":"1.0","canonical_sha256":"0952113d99634e7ff4eb7ae3dce085c79c987c537d4517fff189bb977abdd2fa","source":{"kind":"arxiv","id":"1812.01894","version":1},"attestation_state":"computed","paper":{"title":"Learning to generate filters for convolutional neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Rujie Liu, Wei Shen","submitted_at":"2018-12-05T10:16:38Z","abstract_excerpt":"Conventionally, convolutional neural networks (CNNs) process different images with the same set of filters. However, the variations in images pose a challenge to this fashion. In this paper, we propose to generate sample-specific filters for convolutional layers in the forward pass. Since the filters are generated on-the-fly, the model becomes more flexible and can better fit the training data compared to traditional CNNs. In order to obtain sample-specific features, we extract the intermediate feature maps from an autoencoder. As filters are usually high dimensional, we propose to learn a set"},"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":"1812.01894","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-05T10:16:38Z","cross_cats_sorted":[],"title_canon_sha256":"6e0ac962828b0f285cf6914bb98ae0f52782d48aef529a6d473274888fa8553a","abstract_canon_sha256":"c7388adf34d13ac21d8b6b5220f89fb5e2ff9e862f55bfd32b6cf8c428750604"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:00.299799Z","signature_b64":"rnQIwjJWswTd9KJ75g+9KG/aYMQ6WCy+uX7qrdEbOPxwDLAPhsIoB0bOv7583umIkpZZfxrISrhAwu9iXatcBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0952113d99634e7ff4eb7ae3dce085c79c987c537d4517fff189bb977abdd2fa","last_reissued_at":"2026-05-17T23:59:00.299358Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:00.299358Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to generate filters for convolutional neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Rujie Liu, Wei Shen","submitted_at":"2018-12-05T10:16:38Z","abstract_excerpt":"Conventionally, convolutional neural networks (CNNs) process different images with the same set of filters. However, the variations in images pose a challenge to this fashion. In this paper, we propose to generate sample-specific filters for convolutional layers in the forward pass. Since the filters are generated on-the-fly, the model becomes more flexible and can better fit the training data compared to traditional CNNs. In order to obtain sample-specific features, we extract the intermediate feature maps from an autoencoder. As filters are usually high dimensional, we propose to learn a set"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.01894","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":"1812.01894","created_at":"2026-05-17T23:59:00.299426+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.01894v1","created_at":"2026-05-17T23:59:00.299426+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.01894","created_at":"2026-05-17T23:59:00.299426+00:00"},{"alias_kind":"pith_short_12","alias_value":"BFJBCPMZMNHH","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_16","alias_value":"BFJBCPMZMNHH75HL","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_8","alias_value":"BFJBCPMZ","created_at":"2026-05-18T12:32:16.446611+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/BFJBCPMZMNHH75HLPLR5ZYEFY6","json":"https://pith.science/pith/BFJBCPMZMNHH75HLPLR5ZYEFY6.json","graph_json":"https://pith.science/api/pith-number/BFJBCPMZMNHH75HLPLR5ZYEFY6/graph.json","events_json":"https://pith.science/api/pith-number/BFJBCPMZMNHH75HLPLR5ZYEFY6/events.json","paper":"https://pith.science/paper/BFJBCPMZ"},"agent_actions":{"view_html":"https://pith.science/pith/BFJBCPMZMNHH75HLPLR5ZYEFY6","download_json":"https://pith.science/pith/BFJBCPMZMNHH75HLPLR5ZYEFY6.json","view_paper":"https://pith.science/paper/BFJBCPMZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.01894&json=true","fetch_graph":"https://pith.science/api/pith-number/BFJBCPMZMNHH75HLPLR5ZYEFY6/graph.json","fetch_events":"https://pith.science/api/pith-number/BFJBCPMZMNHH75HLPLR5ZYEFY6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BFJBCPMZMNHH75HLPLR5ZYEFY6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BFJBCPMZMNHH75HLPLR5ZYEFY6/action/storage_attestation","attest_author":"https://pith.science/pith/BFJBCPMZMNHH75HLPLR5ZYEFY6/action/author_attestation","sign_citation":"https://pith.science/pith/BFJBCPMZMNHH75HLPLR5ZYEFY6/action/citation_signature","submit_replication":"https://pith.science/pith/BFJBCPMZMNHH75HLPLR5ZYEFY6/action/replication_record"}},"created_at":"2026-05-17T23:59:00.299426+00:00","updated_at":"2026-05-17T23:59:00.299426+00:00"}