{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:U7CUCXP6C77ISN7HM2UOJJ6ZJR","short_pith_number":"pith:U7CUCXP6","schema_version":"1.0","canonical_sha256":"a7c5415dfe17fe8937e766a8e4a7d94c48c070952a69f0e2bbf8323ea97b2247","source":{"kind":"arxiv","id":"2109.06638","version":4},"attestation_state":"computed","paper":{"title":"Learnable Discrete Wavelet Pooling (LDW-Pooling) For Convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Bor-Shiun Wang, Jun-Wei Hsieh, Lipeng Ke, Ming-Ching Chang, Ping-Yang Chen, Siwei Lyu","submitted_at":"2021-09-13T08:02:38Z","abstract_excerpt":"Pooling is a simple but essential layer in modern deep CNN architectures for feature aggregation and extraction. Typical CNN design focuses on the conv layers and activation functions, while leaving the pooling layers with fewer options. We introduce the Learning Discrete Wavelet Pooling (LDW-Pooling) that can be applied universally to replace standard pooling operations to better extract features with improved accuracy and efficiency. Motivated from the wavelet theory, we adopt the low-pass (L) and high-pass (H) filters horizontally and vertically for pooling on a 2D feature map. Feature sign"},"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":"2109.06638","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-09-13T08:02:38Z","cross_cats_sorted":["cs.LG","eess.IV"],"title_canon_sha256":"1c49f907b13b7d7e004b2014135bdb97cc38dad5426afc80b2161ea38031cba6","abstract_canon_sha256":"17ffda4f5c504650af3c7f7da6fe20f84d7af78ae432897acd664e49b7318f34"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:24:13.215804Z","signature_b64":"5daQqIpcCSamILXq6CoED3I/XmTkIk8q+OO+Ug45+okjJdQJQ1oBnmoVucpDtJ4qwQQ7n1hayJjd6Feyw5HeCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7c5415dfe17fe8937e766a8e4a7d94c48c070952a69f0e2bbf8323ea97b2247","last_reissued_at":"2026-07-05T03:24:13.215344Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:24:13.215344Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learnable Discrete Wavelet Pooling (LDW-Pooling) For Convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Bor-Shiun Wang, Jun-Wei Hsieh, Lipeng Ke, Ming-Ching Chang, Ping-Yang Chen, Siwei Lyu","submitted_at":"2021-09-13T08:02:38Z","abstract_excerpt":"Pooling is a simple but essential layer in modern deep CNN architectures for feature aggregation and extraction. Typical CNN design focuses on the conv layers and activation functions, while leaving the pooling layers with fewer options. We introduce the Learning Discrete Wavelet Pooling (LDW-Pooling) that can be applied universally to replace standard pooling operations to better extract features with improved accuracy and efficiency. Motivated from the wavelet theory, we adopt the low-pass (L) and high-pass (H) filters horizontally and vertically for pooling on a 2D feature map. Feature sign"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.06638","kind":"arxiv","version":4},"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/2109.06638/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":"2109.06638","created_at":"2026-07-05T03:24:13.215407+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.06638v4","created_at":"2026-07-05T03:24:13.215407+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.06638","created_at":"2026-07-05T03:24:13.215407+00:00"},{"alias_kind":"pith_short_12","alias_value":"U7CUCXP6C77I","created_at":"2026-07-05T03:24:13.215407+00:00"},{"alias_kind":"pith_short_16","alias_value":"U7CUCXP6C77ISN7H","created_at":"2026-07-05T03:24:13.215407+00:00"},{"alias_kind":"pith_short_8","alias_value":"U7CUCXP6","created_at":"2026-07-05T03:24:13.215407+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.23042","citing_title":"From Coarse to Fine: Learnable Discrete Wavelet Transforms for Efficient 3D Gaussian Splatting","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U7CUCXP6C77ISN7HM2UOJJ6ZJR","json":"https://pith.science/pith/U7CUCXP6C77ISN7HM2UOJJ6ZJR.json","graph_json":"https://pith.science/api/pith-number/U7CUCXP6C77ISN7HM2UOJJ6ZJR/graph.json","events_json":"https://pith.science/api/pith-number/U7CUCXP6C77ISN7HM2UOJJ6ZJR/events.json","paper":"https://pith.science/paper/U7CUCXP6"},"agent_actions":{"view_html":"https://pith.science/pith/U7CUCXP6C77ISN7HM2UOJJ6ZJR","download_json":"https://pith.science/pith/U7CUCXP6C77ISN7HM2UOJJ6ZJR.json","view_paper":"https://pith.science/paper/U7CUCXP6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.06638&json=true","fetch_graph":"https://pith.science/api/pith-number/U7CUCXP6C77ISN7HM2UOJJ6ZJR/graph.json","fetch_events":"https://pith.science/api/pith-number/U7CUCXP6C77ISN7HM2UOJJ6ZJR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U7CUCXP6C77ISN7HM2UOJJ6ZJR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U7CUCXP6C77ISN7HM2UOJJ6ZJR/action/storage_attestation","attest_author":"https://pith.science/pith/U7CUCXP6C77ISN7HM2UOJJ6ZJR/action/author_attestation","sign_citation":"https://pith.science/pith/U7CUCXP6C77ISN7HM2UOJJ6ZJR/action/citation_signature","submit_replication":"https://pith.science/pith/U7CUCXP6C77ISN7HM2UOJJ6ZJR/action/replication_record"}},"created_at":"2026-07-05T03:24:13.215407+00:00","updated_at":"2026-07-05T03:24:13.215407+00:00"}