{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:I2LL2RBI7FOUU7RZNDT6TE35YP","short_pith_number":"pith:I2LL2RBI","schema_version":"1.0","canonical_sha256":"4696bd4428f95d4a7e3968e7e9937dc3d957ef11f3db9623ef252769e903fef5","source":{"kind":"arxiv","id":"2211.08577","version":1},"attestation_state":"computed","paper":{"title":"DCT Perceptron Layer: A Transform Domain Approach for Convolution Layer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Ahmet Enis Cetin, Hongyi Pan, Salih Atici, Xin Zhu","submitted_at":"2022-11-15T23:44:56Z","abstract_excerpt":"In this paper, we propose a novel Discrete Cosine Transform (DCT)-based neural network layer which we call DCT-perceptron to replace the $3\\times3$ Conv2D layers in the Residual neural Network (ResNet). Convolutional filtering operations are performed in the DCT domain using element-wise multiplications by taking advantage of the Fourier and DCT Convolution theorems. A trainable soft-thresholding layer is used as the nonlinearity in the DCT perceptron. Compared to ResNet's Conv2D layer which is spatial-agnostic and channel-specific, the proposed layer is location-specific and channel-specific."},"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":"2211.08577","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-15T23:44:56Z","cross_cats_sorted":["eess.IV"],"title_canon_sha256":"3d286866eff623bdfc0bb417153a32a079cf3ff3271f49ba98acaf92d5773b5f","abstract_canon_sha256":"0108c9bccc1bea4e926a0cf7ad150a548f20a60a9be477493078b10dda54266b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:16:41.674445Z","signature_b64":"Eo+bVTgNI7V3xwNEKhQg2QDBCk94KHv8emTjC2SPMb0npvSYBPUpOO0P1MzU132lACucOSBM4lfci4heSt99AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4696bd4428f95d4a7e3968e7e9937dc3d957ef11f3db9623ef252769e903fef5","last_reissued_at":"2026-07-05T05:16:41.673980Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:16:41.673980Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DCT Perceptron Layer: A Transform Domain Approach for Convolution Layer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Ahmet Enis Cetin, Hongyi Pan, Salih Atici, Xin Zhu","submitted_at":"2022-11-15T23:44:56Z","abstract_excerpt":"In this paper, we propose a novel Discrete Cosine Transform (DCT)-based neural network layer which we call DCT-perceptron to replace the $3\\times3$ Conv2D layers in the Residual neural Network (ResNet). Convolutional filtering operations are performed in the DCT domain using element-wise multiplications by taking advantage of the Fourier and DCT Convolution theorems. A trainable soft-thresholding layer is used as the nonlinearity in the DCT perceptron. Compared to ResNet's Conv2D layer which is spatial-agnostic and channel-specific, the proposed layer is location-specific and channel-specific."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.08577","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/2211.08577/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":"2211.08577","created_at":"2026-07-05T05:16:41.674036+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.08577v1","created_at":"2026-07-05T05:16:41.674036+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.08577","created_at":"2026-07-05T05:16:41.674036+00:00"},{"alias_kind":"pith_short_12","alias_value":"I2LL2RBI7FOU","created_at":"2026-07-05T05:16:41.674036+00:00"},{"alias_kind":"pith_short_16","alias_value":"I2LL2RBI7FOUU7RZ","created_at":"2026-07-05T05:16:41.674036+00:00"},{"alias_kind":"pith_short_8","alias_value":"I2LL2RBI","created_at":"2026-07-05T05:16:41.674036+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/I2LL2RBI7FOUU7RZNDT6TE35YP","json":"https://pith.science/pith/I2LL2RBI7FOUU7RZNDT6TE35YP.json","graph_json":"https://pith.science/api/pith-number/I2LL2RBI7FOUU7RZNDT6TE35YP/graph.json","events_json":"https://pith.science/api/pith-number/I2LL2RBI7FOUU7RZNDT6TE35YP/events.json","paper":"https://pith.science/paper/I2LL2RBI"},"agent_actions":{"view_html":"https://pith.science/pith/I2LL2RBI7FOUU7RZNDT6TE35YP","download_json":"https://pith.science/pith/I2LL2RBI7FOUU7RZNDT6TE35YP.json","view_paper":"https://pith.science/paper/I2LL2RBI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.08577&json=true","fetch_graph":"https://pith.science/api/pith-number/I2LL2RBI7FOUU7RZNDT6TE35YP/graph.json","fetch_events":"https://pith.science/api/pith-number/I2LL2RBI7FOUU7RZNDT6TE35YP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I2LL2RBI7FOUU7RZNDT6TE35YP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I2LL2RBI7FOUU7RZNDT6TE35YP/action/storage_attestation","attest_author":"https://pith.science/pith/I2LL2RBI7FOUU7RZNDT6TE35YP/action/author_attestation","sign_citation":"https://pith.science/pith/I2LL2RBI7FOUU7RZNDT6TE35YP/action/citation_signature","submit_replication":"https://pith.science/pith/I2LL2RBI7FOUU7RZNDT6TE35YP/action/replication_record"}},"created_at":"2026-07-05T05:16:41.674036+00:00","updated_at":"2026-07-05T05:16:41.674036+00:00"}