Presentation Information
[3P-289]DNN models trained on vision and language robustly align with human color perception while models without language do not
*Nipun Ravindu Wickramanayaka1, Masafumi Oizumi1 (1. Grad Sch of Arts and Sciences, Univ of Tokyo, Tokyo, Japan)
Keywords:
Color perception,Deep Neural Network,Gromov–Wasserstein Optimal Transport,CLIP
Abstract Password Authentication
A password is required to view the full text of the abstract. Please refer to the member site for the password.
https://membership.jnss.org/C00/login
https://membership.jnss.org/C00/login
Comment
To browse or post comments, you must log in.Log in
