{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:VX6DG2KAPVDGEYBFJRFBV2BOHK","short_pith_number":"pith:VX6DG2KA","schema_version":"1.0","canonical_sha256":"adfc3369407d466260254c4a1ae82e3aa293c402a6d8019ae0829611cecc20f7","source":{"kind":"arxiv","id":"1712.01361","version":2},"attestation_state":"computed","paper":{"title":"A+D Net: Training a Shadow Detector with Adversarial Shadow Attenuation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dimitris Samaras, Hieu Le, Minh Hoai, Tomas F. Yago Vicente, Vu Nguyen","submitted_at":"2017-12-04T21:14:32Z","abstract_excerpt":"We propose a novel GAN-based framework for detecting shadows in images, in which a shadow detection network (D-Net) is trained together with a shadow attenuation network (A-Net) that generates adversarial training examples. The A-Net modifies the original training images constrained by a simplified physical shadow model and is focused on fooling the D-Net's shadow predictions. Hence, it is effectively augmenting the training data for D-Net with hard-to-predict cases. The D-Net is trained to predict shadows in both original images and generated images from the A-Net. Our experimental results sh"},"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":"1712.01361","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-04T21:14:32Z","cross_cats_sorted":[],"title_canon_sha256":"af114a4c5d87351cf7e8c2a53a741efe78f37f6c95163faf002600085c99aa8c","abstract_canon_sha256":"1a598b332e70296fe9ba76910fb710f1a064ed3e5478adf81d42f83fb7a762b2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:09:37.626345Z","signature_b64":"56n/+DLEzjIuZYYVw/olIvtQoiZe8IPomaIiztA+P79wznywjv3+d3K/oQjB8WJr0f5btn5rvjjW9HLZDQ+PBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"adfc3369407d466260254c4a1ae82e3aa293c402a6d8019ae0829611cecc20f7","last_reissued_at":"2026-05-18T00:09:37.625701Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:09:37.625701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A+D Net: Training a Shadow Detector with Adversarial Shadow Attenuation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dimitris Samaras, Hieu Le, Minh Hoai, Tomas F. Yago Vicente, Vu Nguyen","submitted_at":"2017-12-04T21:14:32Z","abstract_excerpt":"We propose a novel GAN-based framework for detecting shadows in images, in which a shadow detection network (D-Net) is trained together with a shadow attenuation network (A-Net) that generates adversarial training examples. The A-Net modifies the original training images constrained by a simplified physical shadow model and is focused on fooling the D-Net's shadow predictions. Hence, it is effectively augmenting the training data for D-Net with hard-to-predict cases. The D-Net is trained to predict shadows in both original images and generated images from the A-Net. Our experimental results sh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.01361","kind":"arxiv","version":2},"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":"1712.01361","created_at":"2026-05-18T00:09:37.625786+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.01361v2","created_at":"2026-05-18T00:09:37.625786+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.01361","created_at":"2026-05-18T00:09:37.625786+00:00"},{"alias_kind":"pith_short_12","alias_value":"VX6DG2KAPVDG","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_16","alias_value":"VX6DG2KAPVDGEYBF","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_8","alias_value":"VX6DG2KA","created_at":"2026-05-18T12:31:49.984773+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/VX6DG2KAPVDGEYBFJRFBV2BOHK","json":"https://pith.science/pith/VX6DG2KAPVDGEYBFJRFBV2BOHK.json","graph_json":"https://pith.science/api/pith-number/VX6DG2KAPVDGEYBFJRFBV2BOHK/graph.json","events_json":"https://pith.science/api/pith-number/VX6DG2KAPVDGEYBFJRFBV2BOHK/events.json","paper":"https://pith.science/paper/VX6DG2KA"},"agent_actions":{"view_html":"https://pith.science/pith/VX6DG2KAPVDGEYBFJRFBV2BOHK","download_json":"https://pith.science/pith/VX6DG2KAPVDGEYBFJRFBV2BOHK.json","view_paper":"https://pith.science/paper/VX6DG2KA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.01361&json=true","fetch_graph":"https://pith.science/api/pith-number/VX6DG2KAPVDGEYBFJRFBV2BOHK/graph.json","fetch_events":"https://pith.science/api/pith-number/VX6DG2KAPVDGEYBFJRFBV2BOHK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VX6DG2KAPVDGEYBFJRFBV2BOHK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VX6DG2KAPVDGEYBFJRFBV2BOHK/action/storage_attestation","attest_author":"https://pith.science/pith/VX6DG2KAPVDGEYBFJRFBV2BOHK/action/author_attestation","sign_citation":"https://pith.science/pith/VX6DG2KAPVDGEYBFJRFBV2BOHK/action/citation_signature","submit_replication":"https://pith.science/pith/VX6DG2KAPVDGEYBFJRFBV2BOHK/action/replication_record"}},"created_at":"2026-05-18T00:09:37.625786+00:00","updated_at":"2026-05-18T00:09:37.625786+00:00"}