{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:ETTAK3XK7RBQ4MIF3K6JOPHBU6","short_pith_number":"pith:ETTAK3XK","schema_version":"1.0","canonical_sha256":"24e6056eeafc430e3105dabc973ce1a7ba6f3fc30390766688806a26c61f7767","source":{"kind":"arxiv","id":"1604.06318","version":2},"attestation_state":"computed","paper":{"title":"TI-POOLING: transformation-invariant pooling for feature learning in Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dmitry Laptev, Joachim M. Buhmann, Marc Pollefeys, Nikolay Savinov","submitted_at":"2016-04-21T14:17:05Z","abstract_excerpt":"In this paper we present a deep neural network topology that incorporates a simple to implement transformation invariant pooling operator (TI-POOLING). This operator is able to efficiently handle prior knowledge on nuisance variations in the data, such as rotation or scale changes. Most current methods usually make use of dataset augmentation to address this issue, but this requires larger number of model parameters and more training data, and results in significantly increased training time and larger chance of under- or overfitting. The main reason for these drawbacks is that the learned mod"},"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":"1604.06318","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-04-21T14:17:05Z","cross_cats_sorted":[],"title_canon_sha256":"b90b4224916e8bc2c88c24dbbce04e8adfaf31da71c4de06f8761ad9cc55cd06","abstract_canon_sha256":"7f485758e8c7a400891c12fb3a03a994f72ae6f2715ee28917df2a3676eb3180"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:04:05.594179Z","signature_b64":"0DdVCHZ1hWbnifbeuXh6nQCOL+SflzFqY/x1TAeNjhwl57NZzC0CbBzmmDdZm41Cizqi9Z8hfkq8uHIoC6jnCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24e6056eeafc430e3105dabc973ce1a7ba6f3fc30390766688806a26c61f7767","last_reissued_at":"2026-05-18T01:04:05.593682Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:04:05.593682Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TI-POOLING: transformation-invariant pooling for feature learning in Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dmitry Laptev, Joachim M. Buhmann, Marc Pollefeys, Nikolay Savinov","submitted_at":"2016-04-21T14:17:05Z","abstract_excerpt":"In this paper we present a deep neural network topology that incorporates a simple to implement transformation invariant pooling operator (TI-POOLING). This operator is able to efficiently handle prior knowledge on nuisance variations in the data, such as rotation or scale changes. Most current methods usually make use of dataset augmentation to address this issue, but this requires larger number of model parameters and more training data, and results in significantly increased training time and larger chance of under- or overfitting. The main reason for these drawbacks is that the learned mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.06318","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":"1604.06318","created_at":"2026-05-18T01:04:05.593769+00:00"},{"alias_kind":"arxiv_version","alias_value":"1604.06318v2","created_at":"2026-05-18T01:04:05.593769+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.06318","created_at":"2026-05-18T01:04:05.593769+00:00"},{"alias_kind":"pith_short_12","alias_value":"ETTAK3XK7RBQ","created_at":"2026-05-18T12:30:15.759754+00:00"},{"alias_kind":"pith_short_16","alias_value":"ETTAK3XK7RBQ4MIF","created_at":"2026-05-18T12:30:15.759754+00:00"},{"alias_kind":"pith_short_8","alias_value":"ETTAK3XK","created_at":"2026-05-18T12:30:15.759754+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/ETTAK3XK7RBQ4MIF3K6JOPHBU6","json":"https://pith.science/pith/ETTAK3XK7RBQ4MIF3K6JOPHBU6.json","graph_json":"https://pith.science/api/pith-number/ETTAK3XK7RBQ4MIF3K6JOPHBU6/graph.json","events_json":"https://pith.science/api/pith-number/ETTAK3XK7RBQ4MIF3K6JOPHBU6/events.json","paper":"https://pith.science/paper/ETTAK3XK"},"agent_actions":{"view_html":"https://pith.science/pith/ETTAK3XK7RBQ4MIF3K6JOPHBU6","download_json":"https://pith.science/pith/ETTAK3XK7RBQ4MIF3K6JOPHBU6.json","view_paper":"https://pith.science/paper/ETTAK3XK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1604.06318&json=true","fetch_graph":"https://pith.science/api/pith-number/ETTAK3XK7RBQ4MIF3K6JOPHBU6/graph.json","fetch_events":"https://pith.science/api/pith-number/ETTAK3XK7RBQ4MIF3K6JOPHBU6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ETTAK3XK7RBQ4MIF3K6JOPHBU6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ETTAK3XK7RBQ4MIF3K6JOPHBU6/action/storage_attestation","attest_author":"https://pith.science/pith/ETTAK3XK7RBQ4MIF3K6JOPHBU6/action/author_attestation","sign_citation":"https://pith.science/pith/ETTAK3XK7RBQ4MIF3K6JOPHBU6/action/citation_signature","submit_replication":"https://pith.science/pith/ETTAK3XK7RBQ4MIF3K6JOPHBU6/action/replication_record"}},"created_at":"2026-05-18T01:04:05.593769+00:00","updated_at":"2026-05-18T01:04:05.593769+00:00"}