{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:546WGX6PHSSJIB62L4M4ZZ5TVT","short_pith_number":"pith:546WGX6P","schema_version":"1.0","canonical_sha256":"ef3d635fcf3ca49407da5f19cce7b3acf2a1d39253cde7af39d69fc3830e8a93","source":{"kind":"arxiv","id":"1808.01834","version":1},"attestation_state":"computed","paper":{"title":"Detailed Dense Inference with Convolutional Neural Networks via Discrete Wavelet Transform","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daniel Cremers, J\\\"org St\\\"uckler, Lingni Ma, Tao Wu","submitted_at":"2018-08-06T11:57:15Z","abstract_excerpt":"Dense pixelwise prediction such as semantic segmentation is an up-to-date challenge for deep convolutional neural networks (CNNs). Many state-of-the-art approaches either tackle the loss of high-resolution information due to pooling in the encoder stage, or use dilated convolutions or high-resolution lanes to maintain detailed feature maps and predictions. Motivated by the structural analogy between multi-resolution wavelet analysis and the pooling/unpooling layers of CNNs, we introduce discrete wavelet transform (DWT) into the CNN encoder-decoder architecture and propose WCNN. The high-freque"},"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":"1808.01834","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-08-06T11:57:15Z","cross_cats_sorted":[],"title_canon_sha256":"8ebb49712659af5aacaf84963e225d757acc7c9316216980f72fbdfc9c051fc8","abstract_canon_sha256":"7abb83befd20554c52cc4891f1b9d114939983d22c0b0a83348e6805b11835ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:08:49.562307Z","signature_b64":"GB98JbE/7TIgvpKLwPatWWZdtGv95cVr75+Y+afFhNAUsSw0w7f8UGUXeBBzbh01eH2IKdldOYgvpcgtQh4QBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef3d635fcf3ca49407da5f19cce7b3acf2a1d39253cde7af39d69fc3830e8a93","last_reissued_at":"2026-05-18T00:08:49.561745Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:08:49.561745Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Detailed Dense Inference with Convolutional Neural Networks via Discrete Wavelet Transform","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daniel Cremers, J\\\"org St\\\"uckler, Lingni Ma, Tao Wu","submitted_at":"2018-08-06T11:57:15Z","abstract_excerpt":"Dense pixelwise prediction such as semantic segmentation is an up-to-date challenge for deep convolutional neural networks (CNNs). Many state-of-the-art approaches either tackle the loss of high-resolution information due to pooling in the encoder stage, or use dilated convolutions or high-resolution lanes to maintain detailed feature maps and predictions. Motivated by the structural analogy between multi-resolution wavelet analysis and the pooling/unpooling layers of CNNs, we introduce discrete wavelet transform (DWT) into the CNN encoder-decoder architecture and propose WCNN. The high-freque"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.01834","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":"1808.01834","created_at":"2026-05-18T00:08:49.561849+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.01834v1","created_at":"2026-05-18T00:08:49.561849+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.01834","created_at":"2026-05-18T00:08:49.561849+00:00"},{"alias_kind":"pith_short_12","alias_value":"546WGX6PHSSJ","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_16","alias_value":"546WGX6PHSSJIB62","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_8","alias_value":"546WGX6P","created_at":"2026-05-18T12:32:05.422762+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/546WGX6PHSSJIB62L4M4ZZ5TVT","json":"https://pith.science/pith/546WGX6PHSSJIB62L4M4ZZ5TVT.json","graph_json":"https://pith.science/api/pith-number/546WGX6PHSSJIB62L4M4ZZ5TVT/graph.json","events_json":"https://pith.science/api/pith-number/546WGX6PHSSJIB62L4M4ZZ5TVT/events.json","paper":"https://pith.science/paper/546WGX6P"},"agent_actions":{"view_html":"https://pith.science/pith/546WGX6PHSSJIB62L4M4ZZ5TVT","download_json":"https://pith.science/pith/546WGX6PHSSJIB62L4M4ZZ5TVT.json","view_paper":"https://pith.science/paper/546WGX6P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.01834&json=true","fetch_graph":"https://pith.science/api/pith-number/546WGX6PHSSJIB62L4M4ZZ5TVT/graph.json","fetch_events":"https://pith.science/api/pith-number/546WGX6PHSSJIB62L4M4ZZ5TVT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/546WGX6PHSSJIB62L4M4ZZ5TVT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/546WGX6PHSSJIB62L4M4ZZ5TVT/action/storage_attestation","attest_author":"https://pith.science/pith/546WGX6PHSSJIB62L4M4ZZ5TVT/action/author_attestation","sign_citation":"https://pith.science/pith/546WGX6PHSSJIB62L4M4ZZ5TVT/action/citation_signature","submit_replication":"https://pith.science/pith/546WGX6PHSSJIB62L4M4ZZ5TVT/action/replication_record"}},"created_at":"2026-05-18T00:08:49.561849+00:00","updated_at":"2026-05-18T00:08:49.561849+00:00"}