{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/ad-net-training-a-shadow-detector-with","title":"A+D Net: Training a Shadow Detector with Adversarial Shadow Attenuation","arxiv_id":"1712.01361","date":"2017-12-04","proceeding":"ECCV 2018 9","authors":["Hieu Le","Tomas F. Yago Vicente","Vu Nguyen","Minh Hoai","Dimitris Samaras"],"abstract":"We propose a novel GAN-based framework for detecting shadows in images, in\nwhich a shadow detection network (D-Net) is trained together with a shadow\nattenuation network (A-Net) that generates adversarial training examples. The\nA-Net modifies the original training images constrained by a simplified\nphysical shadow model and is focused on fooling the D-Net's shadow predictions.\nHence, it is effectively augmenting the training data for D-Net with\nhard-to-predict cases. The D-Net is trained to predict shadows in both original\nimages and generated images from the A-Net. Our experimental results show that\nthe additional training data from A-Net significantly improves the shadow\ndetection accuracy of D-Net. Our method outperforms the state-of-the-art\nmethods on the most challenging shadow detection benchmark (SBU) and also\nobtains state-of-the-art results on a cross-dataset task, testing on UCF.\nFurthermore, the proposed method achieves accurate real-time shadow detection\nat 45 frames per second.","url_abs":"http://arxiv.org/abs/1712.01361v2","url_pdf":"http://arxiv.org/pdf/1712.01361v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"ad-net-training-a-shadow-detector-with","repo_url":"https://github.com/lmhieu612/adnet_demo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"detecting-shadows","task_name":"Detecting Shadows"},{"task_slug":"shadow-detection","task_name":"Shadow Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1712.01361","atlas_url":"https://app.syntology.ai/?focus=1712.01361","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}