no code implementations • 8 Dec 2022 • Jiafu Wei, Ding Xia, Haoran Xie, Chia-Ming Chang, Chuntao Li, Xi Yang
We propose an interactive editing method that allows humans to help deep neural networks (DNNs) learn a latent space more consistent with human knowledge, thereby improving classification accuracy on indistinguishable ambiguous data.
1 code implementation • 30 Nov 2022 • Tianyu Zhang, Xusheng Du, Chia-Ming Chang, Xi Yang, Haoran Xie
However, it is difficult to draw a proper scene graph for image retrieval, image generation, and multi-modal applications.
1 code implementation • 13 Jun 2022 • Yi He, Xi Yang, Chia-Ming Chang, Haoran Xie, Takeo Igarashi
Attention guidance is an approach to addressing dataset bias in deep learning, where the model relies on incorrect features to make decisions.
no code implementations • 26 Sep 2021 • Chia-Ming Chang, Tsung-Nan Lin
However, these methods are often subject to performance degradation when domain shifts are confronted.