{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:W7O3ZTQH2VLG756EHM43T2Y4EC","short_pith_number":"pith:W7O3ZTQH","schema_version":"1.0","canonical_sha256":"b7ddbcce07d5566ff7c43b39b9eb1c20b78b831cbff12973abbdb519c001c650","source":{"kind":"arxiv","id":"1711.08591","version":1},"attestation_state":"computed","paper":{"title":"Regularization of Deep Neural Networks with Spectral Dropout","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fatih Porikli, Munawar Hayat, Salman Khan","submitted_at":"2017-11-23T06:47:37Z","abstract_excerpt":"The big breakthrough on the ImageNet challenge in 2012 was partially due to the `dropout' technique used to avoid overfitting. Here, we introduce a new approach called `Spectral Dropout' to improve the generalization ability of deep neural networks. We cast the proposed approach in the form of regular Convolutional Neural Network (CNN) weight layers using a decorrelation transform with fixed basis functions. Our spectral dropout method prevents overfitting by eliminating weak and `noisy' Fourier domain coefficients of the neural network activations, leading to remarkably better results than th"},"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":"1711.08591","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-23T06:47:37Z","cross_cats_sorted":[],"title_canon_sha256":"2314a66e7e6ce9ccf3dd475a2fda552b882a7b5f98d81fe65fba5da629e6d648","abstract_canon_sha256":"d5bb3112ef1d2f8939b98f277533ce3a0fa99c673d9a639d836bfefa7c84c910"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:29:44.637043Z","signature_b64":"2GoXAvDuh3pU/1RC2iTE0vFCSGJrgSOwl/Bk22FYBN0Pwi8eQeEx4Wky+IQUeU4Gy0hLVrC6/BPMYeCOgUuBDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7ddbcce07d5566ff7c43b39b9eb1c20b78b831cbff12973abbdb519c001c650","last_reissued_at":"2026-05-18T00:29:44.636451Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:29:44.636451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Regularization of Deep Neural Networks with Spectral Dropout","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fatih Porikli, Munawar Hayat, Salman Khan","submitted_at":"2017-11-23T06:47:37Z","abstract_excerpt":"The big breakthrough on the ImageNet challenge in 2012 was partially due to the `dropout' technique used to avoid overfitting. Here, we introduce a new approach called `Spectral Dropout' to improve the generalization ability of deep neural networks. We cast the proposed approach in the form of regular Convolutional Neural Network (CNN) weight layers using a decorrelation transform with fixed basis functions. Our spectral dropout method prevents overfitting by eliminating weak and `noisy' Fourier domain coefficients of the neural network activations, leading to remarkably better results than th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.08591","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":"1711.08591","created_at":"2026-05-18T00:29:44.636533+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.08591v1","created_at":"2026-05-18T00:29:44.636533+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.08591","created_at":"2026-05-18T00:29:44.636533+00:00"},{"alias_kind":"pith_short_12","alias_value":"W7O3ZTQH2VLG","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_16","alias_value":"W7O3ZTQH2VLG756E","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_8","alias_value":"W7O3ZTQH","created_at":"2026-05-18T12:31:53.515858+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/W7O3ZTQH2VLG756EHM43T2Y4EC","json":"https://pith.science/pith/W7O3ZTQH2VLG756EHM43T2Y4EC.json","graph_json":"https://pith.science/api/pith-number/W7O3ZTQH2VLG756EHM43T2Y4EC/graph.json","events_json":"https://pith.science/api/pith-number/W7O3ZTQH2VLG756EHM43T2Y4EC/events.json","paper":"https://pith.science/paper/W7O3ZTQH"},"agent_actions":{"view_html":"https://pith.science/pith/W7O3ZTQH2VLG756EHM43T2Y4EC","download_json":"https://pith.science/pith/W7O3ZTQH2VLG756EHM43T2Y4EC.json","view_paper":"https://pith.science/paper/W7O3ZTQH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.08591&json=true","fetch_graph":"https://pith.science/api/pith-number/W7O3ZTQH2VLG756EHM43T2Y4EC/graph.json","fetch_events":"https://pith.science/api/pith-number/W7O3ZTQH2VLG756EHM43T2Y4EC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W7O3ZTQH2VLG756EHM43T2Y4EC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W7O3ZTQH2VLG756EHM43T2Y4EC/action/storage_attestation","attest_author":"https://pith.science/pith/W7O3ZTQH2VLG756EHM43T2Y4EC/action/author_attestation","sign_citation":"https://pith.science/pith/W7O3ZTQH2VLG756EHM43T2Y4EC/action/citation_signature","submit_replication":"https://pith.science/pith/W7O3ZTQH2VLG756EHM43T2Y4EC/action/replication_record"}},"created_at":"2026-05-18T00:29:44.636533+00:00","updated_at":"2026-05-18T00:29:44.636533+00:00"}