Sign in

IncepFormer: Efficient Inception Transformer with Pyramid Pooling for Semantic Segmentation.

Lihua FuHaoyue TianXiangping Bryce ZhaiPan GaoXiaojiang Peng
Published in: CoRR (2022)
Keyphrases
  • semantic segmentation
  • superpixels
  • street scenes
  • multiresolution
  • input image
  • conditional random fields
  • computer vision
  • multiscale
  • d objects
  • scale space
  • scene classification