activity
20222026
most citedCharFormer: A Glyph Fusion based Attentive Framework for High-precision Character Image Denoising

31 citations · 63 across the 14 of their papers we have counts for

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2022

SpaceEditing: Integrating Human Knowledge into Deep Neural Networks via Interactive Latent Space Editing

Jiafu Wei, Ding Xia, Haoran Xie +3

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 classif…