PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment

Code

• github.com/kaixin96/PANet
  Officialpytorch★ 0
• github.com/fanq15/ssp
  pytorch★ 111
• github.com/LiheYoung/MiningFSS
  pytorch★ 75
• github.com/CSCYQJ/LOCATION-SENSITIVE-LOCAL-PROTOTYPE-NETWORK
  pytorch★ 10
• github.com/RogerQi/pascal-5i
  pytorch★ 0

Abstract

Despite the great progress made by deep CNNs in image semantic segmentation, they typically require a large number of densely-annotated images for training and are difficult to generalize to unseen object categories. Few-shot segmentation has thus been developed to learn to perform segmentation from only a few annotated examples. In this paper, we tackle the challenging few-shot segmentation problem from a metric learning perspective and present PANet, a novel prototype alignment network to better utilize the information of the support set. Our PANet learns class-specific prototype representations from a few support images within an embedding space and then performs segmentation over the query images through matching each pixel to the learned prototypes. With non-parametric metric learning, PANet offers high-quality prototypes that are representative for each semantic class and meanwhile discriminative for different classes. Moreover, PANet introduces a prototype alignment regularization between support and query. With this, PANet fully exploits knowledge from the support and provides better generalization on few-shot segmentation. Significantly, our model achieves the mIoU score of 48.1% and 55.7% on PASCAL-5i for 1-shot and 5-shot settings respectively, surpassing the state-of-the-art method by 1.8% and 8.6%.

Tasks

Benchmark Results

Reproductions