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

Zhang, Chi; Lin, Guosheng; Liu, Fayao; Yao, Rui; Shen, Chunhua

doi:10.1109/cvpr.2019.00536

preprintJun 1, 2019GREEN OA

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

CZChi Zhang GLGuosheng Lin FLFayao Liu RYRui Yao CSChunhua Shen

Nanyang Technological University · University of Adelaide · +1 more institution

Indexed incrossref

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…

Citation impact

659

total citations

FWCI: 41.07
Percentile: 100%
References: 67

Citations per year

Authors

5

Topics & keywords

Topics

Keywords

Computer science
Segmentation
Artificial intelligence
Shot (pellet)
Class (philosophy)
Iterative learning control
Image segmentation
One shot

No related works found for this paper.