{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:YYE2NNCWF5DGJLBHL6QKTMBZB5","short_pith_number":"pith:YYE2NNCW","schema_version":"1.0","canonical_sha256":"c609a6b4562f4664ac275fa0a9b0390f689bd0fde5d13488f8eb184e626bc9c1","source":{"kind":"arxiv","id":"2111.00772","version":3},"attestation_state":"computed","paper":{"title":"AdaPool: Exponential Adaptive Pooling for Information-Retaining Downsampling","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexandros Stergiou, Ronald Poppe","submitted_at":"2021-11-01T08:50:37Z","abstract_excerpt":"Pooling layers are essential building blocks of convolutional neural networks (CNNs), to reduce computational overhead and increase the receptive fields of proceeding convolutional operations. Their goal is to produce downsampled volumes that closely resemble the input volume while, ideally, also being computationally and memory efficient. Meeting both these requirements remains a challenge. To this end, we propose an adaptive and exponentially weighted pooling method: adaPool. Our method learns a regional-specific fusion of two sets of pooling kernels that are based on the exponent of the Dic"},"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":"2111.00772","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-01T08:50:37Z","cross_cats_sorted":[],"title_canon_sha256":"0b2e7aa3c77b91bea7de627772b7012dcefbe32fb287186303e01fd4717f8233","abstract_canon_sha256":"3926a99459b35c672a51734dbc0393f38bd48c1f7fcde1a1220b367a3b23f671"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:21:40.104416Z","signature_b64":"jW28HXyK9a8KUceXMd0z5cWhgteoWiS7+CuQpzn8CNRyXfWeGui6DZBFjSKMiWERyFCMSEpw1JZDBt4m0uv/BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c609a6b4562f4664ac275fa0a9b0390f689bd0fde5d13488f8eb184e626bc9c1","last_reissued_at":"2026-07-05T05:21:40.104068Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:21:40.104068Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AdaPool: Exponential Adaptive Pooling for Information-Retaining Downsampling","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexandros Stergiou, Ronald Poppe","submitted_at":"2021-11-01T08:50:37Z","abstract_excerpt":"Pooling layers are essential building blocks of convolutional neural networks (CNNs), to reduce computational overhead and increase the receptive fields of proceeding convolutional operations. Their goal is to produce downsampled volumes that closely resemble the input volume while, ideally, also being computationally and memory efficient. Meeting both these requirements remains a challenge. To this end, we propose an adaptive and exponentially weighted pooling method: adaPool. Our method learns a regional-specific fusion of two sets of pooling kernels that are based on the exponent of the Dic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.00772","kind":"arxiv","version":3},"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/2111.00772/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":"2111.00772","created_at":"2026-07-05T05:21:40.104123+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.00772v3","created_at":"2026-07-05T05:21:40.104123+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.00772","created_at":"2026-07-05T05:21:40.104123+00:00"},{"alias_kind":"pith_short_12","alias_value":"YYE2NNCWF5DG","created_at":"2026-07-05T05:21:40.104123+00:00"},{"alias_kind":"pith_short_16","alias_value":"YYE2NNCWF5DGJLBH","created_at":"2026-07-05T05:21:40.104123+00:00"},{"alias_kind":"pith_short_8","alias_value":"YYE2NNCW","created_at":"2026-07-05T05:21:40.104123+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/YYE2NNCWF5DGJLBHL6QKTMBZB5","json":"https://pith.science/pith/YYE2NNCWF5DGJLBHL6QKTMBZB5.json","graph_json":"https://pith.science/api/pith-number/YYE2NNCWF5DGJLBHL6QKTMBZB5/graph.json","events_json":"https://pith.science/api/pith-number/YYE2NNCWF5DGJLBHL6QKTMBZB5/events.json","paper":"https://pith.science/paper/YYE2NNCW"},"agent_actions":{"view_html":"https://pith.science/pith/YYE2NNCWF5DGJLBHL6QKTMBZB5","download_json":"https://pith.science/pith/YYE2NNCWF5DGJLBHL6QKTMBZB5.json","view_paper":"https://pith.science/paper/YYE2NNCW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.00772&json=true","fetch_graph":"https://pith.science/api/pith-number/YYE2NNCWF5DGJLBHL6QKTMBZB5/graph.json","fetch_events":"https://pith.science/api/pith-number/YYE2NNCWF5DGJLBHL6QKTMBZB5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YYE2NNCWF5DGJLBHL6QKTMBZB5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YYE2NNCWF5DGJLBHL6QKTMBZB5/action/storage_attestation","attest_author":"https://pith.science/pith/YYE2NNCWF5DGJLBHL6QKTMBZB5/action/author_attestation","sign_citation":"https://pith.science/pith/YYE2NNCWF5DGJLBHL6QKTMBZB5/action/citation_signature","submit_replication":"https://pith.science/pith/YYE2NNCWF5DGJLBHL6QKTMBZB5/action/replication_record"}},"created_at":"2026-07-05T05:21:40.104123+00:00","updated_at":"2026-07-05T05:21:40.104123+00:00"}