iMTE

논문 제목 : Grad-CAM: Why did you say that? 논문 주소 : https://arxiv.org/abs/1611.07450 Grad-CAM: Why did you say that? We propose a technique for making Convolutional Neural Network (CNN)-based models more transparent by visualizing input regions that are 'important' for predictions -- or visual explanations. Our approach, called Gradient-weighted Class Activation Mapping arxiv.org 주요 내용 정리: 1) Grad-C..

논문 제목 : SS-CAM: Smoothed Score-CAM for Sharper Visual Feature Localization 논문 주소 : https://arxiv.org/abs/2006.14255 SS-CAM: Smoothed Score-CAM for Sharper Visual Feature Localization Interpretation of the underlying mechanisms of Deep Convolutional Neural Networks has become an important aspect of research in the field of deep learning due to their applications in high-risk environments. To expl..

논문 제목 : Score-CAM : Score-weighted visual explanations for convolutional neural networks 논문 주소 : https://openaccess.thecvf.com/content_CVPRW_2020/html/w1/Wang_Score-CAM_Score-Weighted_Visual_Explanations_for_Convolutional_Neural_Networks_CVPRW_2020_paper.html CVPR 2020 Open Access Repository Haofan Wang, Zifan Wang, Mengnan Du, Fan Yang, Zijian Zhang, Sirui Ding, Piotr Mardziel, Xia Hu; Proceedi..

논문 제목 : Adapting Grad-CAM for Embedding Networks 논문 주소 : https://openaccess.thecvf.com/content_WACV_2020/html/Chen_Adapting_Grad-CAM_for_Embedding_Networks_WACV_2020_paper.html WACV 2020 Open Access Repository Lei Chen, Jianhui Chen, Hossein Hajimirsadeghi, Greg Mori; Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2020, pp. 2794-2803 The gradient-weighte..