{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:LWBG7UPE7W6NXM5JGRJFT4S55P","short_pith_number":"pith:LWBG7UPE","schema_version":"1.0","canonical_sha256":"5d826fd1e4fdbcdbb3a9345259f25debe92d10c4d477d3fe60d3dc9bf1aea228","source":{"kind":"arxiv","id":"2012.14123","version":5},"attestation_state":"computed","paper":{"title":"Spectral Analysis for Semantic Segmentation with Applications on Feature Truncation and Weak Annotation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chin-Tien Wu, Li-Wei Chen, Wei-Chen Chiu","submitted_at":"2020-12-28T07:18:25Z","abstract_excerpt":"It is well known that semantic segmentation neural networks (SSNNs) produce dense segmentation maps to resolve the objects' boundaries while restrict the prediction on down-sampled grids to alleviate the computational cost. A striking balance between the accuracy and the training cost of the SSNNs such as U-Net exists. We propose a spectral analysis to investigate the correlations among the resolution of the down sampled grid, the loss function and the accuracy of the SSNNs. By analyzing the network back-propagation process in frequency domain, we discover that the traditional loss function, c"},"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":"2012.14123","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-12-28T07:18:25Z","cross_cats_sorted":[],"title_canon_sha256":"b3d40208cc3e1af933949836d192947a2a44a8ab54475fd26249267b3c2539b1","abstract_canon_sha256":"af4d0eabfedd78a2607f6849e531b568816f57c78f54df0e7de5d03405d719c5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:09:02.876989Z","signature_b64":"uIKPzyshSyqCgNKOWKWbIoudtqv4OxcPKpeASxJvQxpwiEtVZv75nV3niMJCfe4kh2LhA3CmUI3Hs11cI42vBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d826fd1e4fdbcdbb3a9345259f25debe92d10c4d477d3fe60d3dc9bf1aea228","last_reissued_at":"2026-07-05T06:09:02.876515Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:09:02.876515Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spectral Analysis for Semantic Segmentation with Applications on Feature Truncation and Weak Annotation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chin-Tien Wu, Li-Wei Chen, Wei-Chen Chiu","submitted_at":"2020-12-28T07:18:25Z","abstract_excerpt":"It is well known that semantic segmentation neural networks (SSNNs) produce dense segmentation maps to resolve the objects' boundaries while restrict the prediction on down-sampled grids to alleviate the computational cost. A striking balance between the accuracy and the training cost of the SSNNs such as U-Net exists. We propose a spectral analysis to investigate the correlations among the resolution of the down sampled grid, the loss function and the accuracy of the SSNNs. By analyzing the network back-propagation process in frequency domain, we discover that the traditional loss function, c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.14123","kind":"arxiv","version":5},"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/2012.14123/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":"2012.14123","created_at":"2026-07-05T06:09:02.876572+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.14123v5","created_at":"2026-07-05T06:09:02.876572+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.14123","created_at":"2026-07-05T06:09:02.876572+00:00"},{"alias_kind":"pith_short_12","alias_value":"LWBG7UPE7W6N","created_at":"2026-07-05T06:09:02.876572+00:00"},{"alias_kind":"pith_short_16","alias_value":"LWBG7UPE7W6NXM5J","created_at":"2026-07-05T06:09:02.876572+00:00"},{"alias_kind":"pith_short_8","alias_value":"LWBG7UPE","created_at":"2026-07-05T06:09:02.876572+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/LWBG7UPE7W6NXM5JGRJFT4S55P","json":"https://pith.science/pith/LWBG7UPE7W6NXM5JGRJFT4S55P.json","graph_json":"https://pith.science/api/pith-number/LWBG7UPE7W6NXM5JGRJFT4S55P/graph.json","events_json":"https://pith.science/api/pith-number/LWBG7UPE7W6NXM5JGRJFT4S55P/events.json","paper":"https://pith.science/paper/LWBG7UPE"},"agent_actions":{"view_html":"https://pith.science/pith/LWBG7UPE7W6NXM5JGRJFT4S55P","download_json":"https://pith.science/pith/LWBG7UPE7W6NXM5JGRJFT4S55P.json","view_paper":"https://pith.science/paper/LWBG7UPE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.14123&json=true","fetch_graph":"https://pith.science/api/pith-number/LWBG7UPE7W6NXM5JGRJFT4S55P/graph.json","fetch_events":"https://pith.science/api/pith-number/LWBG7UPE7W6NXM5JGRJFT4S55P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LWBG7UPE7W6NXM5JGRJFT4S55P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LWBG7UPE7W6NXM5JGRJFT4S55P/action/storage_attestation","attest_author":"https://pith.science/pith/LWBG7UPE7W6NXM5JGRJFT4S55P/action/author_attestation","sign_citation":"https://pith.science/pith/LWBG7UPE7W6NXM5JGRJFT4S55P/action/citation_signature","submit_replication":"https://pith.science/pith/LWBG7UPE7W6NXM5JGRJFT4S55P/action/replication_record"}},"created_at":"2026-07-05T06:09:02.876572+00:00","updated_at":"2026-07-05T06:09:02.876572+00:00"}