Adaptive Prototype Learning and Allocation for Few-Shot Segmentation
Authors:
Top Cited Papers
- 1 June 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 8330-8339
Abstract
Prototype learning is extensively used for few-shot segmentation. Typically, a single prototype is obtained from the support feature by averaging the global object information. However, using one prototype to represent all the information may lead to ambiguities. In this paper, we propose two novel modules, named superpixel-guided clustering (SGC) and guided prototype allocation (GPA), for multiple prototype extraction and allocation. Specifically, SGC is a parameter-free and training-free approach, which extracts more representative prototypes by aggregating similar feature vectors, while GPA is able to select matched prototypes to provide more accurate guidance. By integrating the SGC and GPA together, we propose the Adaptive Superpixel-guided Network (ASGNet), which is a lightweight model and adapts to object scale and shape variation. In addition, our network can easily generalize to k-shot segmentation with substantial improvement and no additional computational cost. In particular, our evaluations on COCO demonstrate that ASGNet surpasses the state-of-the-art method by 5% in 5-shot segmentation. 1Keywords
All Related Versions
This publication has 25 references indexed in Scilit:
- Learning to Compare: Relation Network for Few-Shot Learning2018
- Superpixels: An evaluation of the state-of-the-artComputer Vision and Image Understanding, 2018
- Feature Pyramid Networks for Object Detection2017
- Pyramid Scene Parsing Network2017
- ImageNet classification with deep convolutional neural networksCommunications of the ACM, 2017
- Deep Residual Learning for Image Recognition2016
- Fully convolutional networks for semantic segmentation2015
- SLIC Superpixels Compared to State-of-the-Art Superpixel MethodsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012
- Semantic contours from inverse detectors2011
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009