Login / Signup

ALGM: Adaptive Local-then-Global Token Merging for Efficient Semantic Segmentation with Plain Vision Transformers.

Narges NorouziSvetlana OrlovaDaan de GeusGijs Dubbelman
Published in: CoRR (2024)
Keyphrases
  • semantic segmentation
  • computer vision
  • street scenes
  • image processing
  • pairwise
  • object detection
  • image classification
  • conditional random fields
  • object categories
  • graph structure
  • superpixels
  • scene classification