no code implementations • 4 Oct 2023 • Seok-Yong Byun, Wonju Lee
Our proposed method provides an efficient and easy-to-implement alternative for generating visual explanations, without requiring attention and gradient information, which can be beneficial for various applications in the field of computer vision.
1 code implementation • 28 Sep 2022 • Seok-Yong Byun, Wonju Lee
To overcome this issue, Score-CAM and Ablation-CAM have been proposed as gradient-free methods, but they have longer execution times compared to CAM or Grad-CAM based methods, making them unsuitable for real-world solution though they resolved gradient related issues and enabled inference mode XAI.
no code implementations • 1 Jul 2021 • Wonju Lee, Seok-Yong Byun, Jooeun Kim, Minje Park, Kirill Chechil
While many real-world data streams imply that they change frequently in a nonstationary way, most of deep learning methods optimize neural networks on training data, and this leads to severe performance degradation when dataset shift happens.