CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learning

Abstract

Recent progress in semantic segmentation is driven by deep Convolutional Neural Networks and large-scale labeled image datasets. However, data labeling for pixel-wise segmentation is tedious and costly. Moreover, a trained model can only make predictions within a set of pre-defined classes. In this paper, we present CANet, a class-agnostic segmentation network that performs few-shot segmentation on new classes with only a few annotated images available. Our network consists of a two-branch dense comparison module which performs multi-level feature comparison between the support image and the query image, and an iterative optimization module which iteratively refines the predicted results. Furthermore, we introduce an attention mechanism to effectively fuse information from multiple support examples under the setting of k-shot learning. Experiments on PASCAL VOC 2012 show that our method achieves a mean Intersection-over-Union score of 55.4% for 1-shot segmentation and 57.1% for 5-shot segmentation, outperforming state-of-the-art methods by a large margin of 14.6% and 13.2%, respectively.

Accepted to CVPR 2019

References in corpus (14)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Rethinking Atrous Convolution for Semantic Image Segmentation
• Prototypical Networks for Few-shot Learning
• Deep Residual Learning for Image Recognition
• Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
• Understanding Neural Networks Through Deep Visualization
• ParseNet: Looking Wider to See Better
• Matching Networks for One Shot Learning
• Fully Convolutional Networks for Semantic Segmentation
• Pyramid Scene Parsing Network
• Learning feed-forward one-shot learners
• Deep Interactive Object Selection
• Weakly-Supervised Semantic Segmentation by Iteratively Mining Common Object Features
• Learning to Segment Every Thing

Cited by in corpus (4)

• Prior Guided Feature Enrichment Network for Few-Shot Segmentation
• PFENet++: Boosting Few-shot Semantic Segmentation with the Noise-filtered Context-aware Prior Mask
• Differentiable Meta-learning Model for Few-shot Semantic Segmentation
• Boundary Knowledge Translation based Reference Semantic Segmentation