{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:MPWYDU2UPZWTAJM3JURU5W3VPM","short_pith_number":"pith:MPWYDU2U","schema_version":"1.0","canonical_sha256":"63ed81d3547e6d30259b4d234edb757b2574b7845e879a0fcb8c1422c64be753","source":{"kind":"arxiv","id":"1909.00114","version":1},"attestation_state":"computed","paper":{"title":"Towards Learning Affine-Invariant Representations via Data-Efficient CNNs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alan Sullivan, Guanghui Wang, Xenju Xu, Ziming Zhang","submitted_at":"2019-08-31T03:11:59Z","abstract_excerpt":"In this paper we propose integrating a priori knowledge into both design and training of convolutional neural networks (CNNs) to learn object representations that are invariant to affine transformations (i.e., translation, scale, rotation). Accordingly we propose a novel multi-scale maxout CNN and train it end-to-end with a novel rotation-invariant regularizer. This regularizer aims to enforce the weights in each 2D spatial filter to approximate circular patterns. In this way, we manage to handle affine transformations in training using convolution, multi-scale maxout, and circular filters. Em"},"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":"1909.00114","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-31T03:11:59Z","cross_cats_sorted":[],"title_canon_sha256":"953ad10b5c1895f2caa48638698cef5b920f00c9c5f5991e92ab02ff396237c6","abstract_canon_sha256":"a1bbc46fbffa9b5ad13680b8002db402ff8fe1a08ca98e0c00ec8e0b92f8b4dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:01:05.616358Z","signature_b64":"2zGDcLWW5khSXXPCaN1ZoS2OPSw+92a4r3Nc2tGlcAxWUFpyO6aJZg0jL0jGnQZkasdeZ9jNrjE/0wylD88BBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63ed81d3547e6d30259b4d234edb757b2574b7845e879a0fcb8c1422c64be753","last_reissued_at":"2026-07-05T00:01:05.615858Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:01:05.615858Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Learning Affine-Invariant Representations via Data-Efficient CNNs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alan Sullivan, Guanghui Wang, Xenju Xu, Ziming Zhang","submitted_at":"2019-08-31T03:11:59Z","abstract_excerpt":"In this paper we propose integrating a priori knowledge into both design and training of convolutional neural networks (CNNs) to learn object representations that are invariant to affine transformations (i.e., translation, scale, rotation). Accordingly we propose a novel multi-scale maxout CNN and train it end-to-end with a novel rotation-invariant regularizer. This regularizer aims to enforce the weights in each 2D spatial filter to approximate circular patterns. In this way, we manage to handle affine transformations in training using convolution, multi-scale maxout, and circular filters. Em"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.00114","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1909.00114/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"1909.00114","created_at":"2026-07-05T00:01:05.615931+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.00114v1","created_at":"2026-07-05T00:01:05.615931+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.00114","created_at":"2026-07-05T00:01:05.615931+00:00"},{"alias_kind":"pith_short_12","alias_value":"MPWYDU2UPZWT","created_at":"2026-07-05T00:01:05.615931+00:00"},{"alias_kind":"pith_short_16","alias_value":"MPWYDU2UPZWTAJM3","created_at":"2026-07-05T00:01:05.615931+00:00"},{"alias_kind":"pith_short_8","alias_value":"MPWYDU2U","created_at":"2026-07-05T00:01:05.615931+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/MPWYDU2UPZWTAJM3JURU5W3VPM","json":"https://pith.science/pith/MPWYDU2UPZWTAJM3JURU5W3VPM.json","graph_json":"https://pith.science/api/pith-number/MPWYDU2UPZWTAJM3JURU5W3VPM/graph.json","events_json":"https://pith.science/api/pith-number/MPWYDU2UPZWTAJM3JURU5W3VPM/events.json","paper":"https://pith.science/paper/MPWYDU2U"},"agent_actions":{"view_html":"https://pith.science/pith/MPWYDU2UPZWTAJM3JURU5W3VPM","download_json":"https://pith.science/pith/MPWYDU2UPZWTAJM3JURU5W3VPM.json","view_paper":"https://pith.science/paper/MPWYDU2U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.00114&json=true","fetch_graph":"https://pith.science/api/pith-number/MPWYDU2UPZWTAJM3JURU5W3VPM/graph.json","fetch_events":"https://pith.science/api/pith-number/MPWYDU2UPZWTAJM3JURU5W3VPM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MPWYDU2UPZWTAJM3JURU5W3VPM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MPWYDU2UPZWTAJM3JURU5W3VPM/action/storage_attestation","attest_author":"https://pith.science/pith/MPWYDU2UPZWTAJM3JURU5W3VPM/action/author_attestation","sign_citation":"https://pith.science/pith/MPWYDU2UPZWTAJM3JURU5W3VPM/action/citation_signature","submit_replication":"https://pith.science/pith/MPWYDU2UPZWTAJM3JURU5W3VPM/action/replication_record"}},"created_at":"2026-07-05T00:01:05.615931+00:00","updated_at":"2026-07-05T00:01:05.615931+00:00"}