文献类型：期刊文献

英文题名：Task Encoding With Distribution Calibration for Few-Shot Learning

作者：Zhang, Jing[1];Zhang, Xinzhou[1];Wang, Zhe[1]

机构：[1]East China Univ Sci & Technol, Dept Comp Sci & Engn, Shanghai 200237, Peoples R China

年份：2022

卷号：32

期号：9

起止页码：6240

外文期刊名：IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY

收录：;EI(收录号：20221511959243);WOS:【SCI-EXPANDED(收录号:WOS:000849300000043)】；

基金：This work was supported by the Shanghai Science and Technology Program "Distributed small sample learning and small sample generation algorithm and theory research" under Grant 20511100600. This article was recommended by Associate Editor F. Diaz-de-Maria.

语种：英文

外文关键词：Task analysis; Feature extraction; Adaptation models; Calibration; Encoding; Computational modeling; Training; Few-shot learning; task encoding; distribution calibration; image classification

摘要：Few-shot learning is an extremely challenging task in computer vision that has attracted increased research attention in recent years. However, most recent methods do not fully use the task's information, and few of the seen samples result in large intraclass differences among the same classes. In this paper, we propose a novel task encoding with distribution calibration (TEDC) model for few-shot learning, which uses the relationships among the feature distributions to reduce intraclass differences. In the TEDC model, an integrated feature extraction module (IFEM) is proposed, which extracts the multiangle visual features of an image and fuses them to obtain more representative features. To effectively utilize the task information, a novel task encoding module (TEM) is proposed, which obtains the task features by fusing all the seen samples' information and uses them to adjust all the samples' features for more generalizable task-specific representations. We also propose a distribution calibration module (DCM) to reduce the bias between the distribution of the support features and the query features in the same class. Extensive experiments show that our proposed TEDC model achieves an excellent performance and outperforms the state-of-the-art methods on three widely used few-shot classification benchmarks, specifically miniImageNet, tieredImageNet and CUB-200-2011.