{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZVLNG7CEWVTSN3QBUGXNI6XR5U","short_pith_number":"pith:ZVLNG7CE","schema_version":"1.0","canonical_sha256":"cd56d37c44b56726ee01a1aed47af1ed34810f06de0a8854f2e713822921442b","source":{"kind":"arxiv","id":"2308.12064","version":1},"attestation_state":"computed","paper":{"title":"SILT: Shadow-aware Iterative Label Tuning for Learning to Detect Shadows from Noisy Labels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chi-Wing Fu, Han Yang, Tianyu Wang, Xiaowei Hu","submitted_at":"2023-08-23T11:16:36Z","abstract_excerpt":"Existing shadow detection datasets often contain missing or mislabeled shadows, which can hinder the performance of deep learning models trained directly on such data. To address this issue, we propose SILT, the Shadow-aware Iterative Label Tuning framework, which explicitly considers noise in shadow labels and trains the deep model in a self-training manner. Specifically, we incorporate strong data augmentations with shadow counterfeiting to help the network better recognize non-shadow regions and alleviate overfitting. We also devise a simple yet effective label tuning strategy with global-l"},"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":"2308.12064","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-23T11:16:36Z","cross_cats_sorted":[],"title_canon_sha256":"38e97a28495a62518c9cfba957b016305f1314008618a826fbdd0a6de6b6bc8c","abstract_canon_sha256":"eee89cd524063defc5a8375ba080ce714c86eb8fa337007cc6e630ccd4b635bc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:43:59.017761Z","signature_b64":"6nyksbEGqo0l7Or68VknSq/fazmakFjVMTiuWAExla/HrMUfriXK4z8GFcjo+OkIWEw9zSdNEfaj39dZVQk7Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd56d37c44b56726ee01a1aed47af1ed34810f06de0a8854f2e713822921442b","last_reissued_at":"2026-07-05T06:43:59.017239Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:43:59.017239Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SILT: Shadow-aware Iterative Label Tuning for Learning to Detect Shadows from Noisy Labels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chi-Wing Fu, Han Yang, Tianyu Wang, Xiaowei Hu","submitted_at":"2023-08-23T11:16:36Z","abstract_excerpt":"Existing shadow detection datasets often contain missing or mislabeled shadows, which can hinder the performance of deep learning models trained directly on such data. To address this issue, we propose SILT, the Shadow-aware Iterative Label Tuning framework, which explicitly considers noise in shadow labels and trains the deep model in a self-training manner. Specifically, we incorporate strong data augmentations with shadow counterfeiting to help the network better recognize non-shadow regions and alleviate overfitting. We also devise a simple yet effective label tuning strategy with global-l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.12064","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/2308.12064/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":"2308.12064","created_at":"2026-07-05T06:43:59.017303+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.12064v1","created_at":"2026-07-05T06:43:59.017303+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.12064","created_at":"2026-07-05T06:43:59.017303+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZVLNG7CEWVTS","created_at":"2026-07-05T06:43:59.017303+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZVLNG7CEWVTSN3QB","created_at":"2026-07-05T06:43:59.017303+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZVLNG7CE","created_at":"2026-07-05T06:43:59.017303+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/ZVLNG7CEWVTSN3QBUGXNI6XR5U","json":"https://pith.science/pith/ZVLNG7CEWVTSN3QBUGXNI6XR5U.json","graph_json":"https://pith.science/api/pith-number/ZVLNG7CEWVTSN3QBUGXNI6XR5U/graph.json","events_json":"https://pith.science/api/pith-number/ZVLNG7CEWVTSN3QBUGXNI6XR5U/events.json","paper":"https://pith.science/paper/ZVLNG7CE"},"agent_actions":{"view_html":"https://pith.science/pith/ZVLNG7CEWVTSN3QBUGXNI6XR5U","download_json":"https://pith.science/pith/ZVLNG7CEWVTSN3QBUGXNI6XR5U.json","view_paper":"https://pith.science/paper/ZVLNG7CE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.12064&json=true","fetch_graph":"https://pith.science/api/pith-number/ZVLNG7CEWVTSN3QBUGXNI6XR5U/graph.json","fetch_events":"https://pith.science/api/pith-number/ZVLNG7CEWVTSN3QBUGXNI6XR5U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZVLNG7CEWVTSN3QBUGXNI6XR5U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZVLNG7CEWVTSN3QBUGXNI6XR5U/action/storage_attestation","attest_author":"https://pith.science/pith/ZVLNG7CEWVTSN3QBUGXNI6XR5U/action/author_attestation","sign_citation":"https://pith.science/pith/ZVLNG7CEWVTSN3QBUGXNI6XR5U/action/citation_signature","submit_replication":"https://pith.science/pith/ZVLNG7CEWVTSN3QBUGXNI6XR5U/action/replication_record"}},"created_at":"2026-07-05T06:43:59.017303+00:00","updated_at":"2026-07-05T06:43:59.017303+00:00"}