Tweeted By @ak92501
Per-Pixel Classification is Not All You Need for Semantic Segmentation
— AK (@ak92501) July 14, 2021
pdf: https://t.co/lG6ZYV8XBp
github: https://t.co/bXqZ6pR3Fb
outperforms both current sota semantic (55.6 mIoU on ADE20K) and panoptic segmentation (52.7 PQ on COCO) models pic.twitter.com/RqNInMJQOm