Saved in:
Bibliographic Details
Main Authors: Linghu, Xiongkun, Bai, Yan, Lou, Yihang, Wu, Shengsen, Li, Jinze, He, Jianzhong, Bai, Tao
Format: Preprint
Published: 2022
Subjects:
Online Access:https://arxiv.org/abs/2207.13137
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Few-Shot Classification(FSC) aims to generalize from base classes to novel classes given very limited labeled samples, which is an important step on the path toward human-like machine learning. State-of-the-art solutions involve learning to find a good metric and representation space to compute the distance between samples. Despite the promising accuracy performance, how to model uncertainty for metric-based FSC methods effectively is still a challenge. To model uncertainty, We place a distribution over class probability based on the theory of evidence. As a result, uncertainty modeling and metric learning can be decoupled. To reduce the uncertainty of classification, we propose a Bayesian evidence fusion theorem. Given observed samples, the network learns to get posterior distribution parameters given the prior parameters produced by the pre-trained network. Detailed gradient analysis shows that our method provides a smooth optimization target and can capture the uncertainty. The proposed method is agnostic to metric learning strategies and can be implemented as a plug-and-play module. We integrate our method into several newest FSC methods and demonstrate the improved accuracy and uncertainty quantification on standard FSC benchmarks.