Login / Signup
Conv2Former: A Simple Transformer-Style ConvNet for Visual Recognition.
Qibin Hou
Chengze Lu
Ming-Ming Cheng
Jiashi Feng
Published in:
CoRR (2022)
Keyphrases
</>
visual recognition
image classification
fault diagnosis
object recognition
view independent
visual categorization
visual recognition tasks
latent topic models
pattern recognition
visual classification
image features
fuzzy logic
natural images
bag of words
category level