Sign in

VNet: a versatile network to train real-time semantic segmentation models on a single GPU.

Wenxing LiNing LinMingzhe ZhangHang LuXiaoming ChenXiaowei Li
Published in: Sci. China Inf. Sci. (2022)
Keyphrases
  • real time
  • semantic segmentation
  • probabilistic model
  • street scenes
  • multiscale
  • superpixels
  • computer vision
  • object recognition
  • prior knowledge
  • object detection
  • conditional random fields
  • long range
  • label transfer