All in Tokens: Unifying Output Space of Visual Tasks via Soft Token.

Jia Ning Chen Li Zheng Zhang Zigang Geng Qi Dai Kun He Han Hu

Published in: CoRR (2023)

Keyphrases

visual tasks
output space
input space
active vision
structured output
representative set
high dimensional
training set
user defined
class labels
high dimensional data
real time
kernel function
small sample
k nearest neighbor
input data
image classification
feature space
training data