Learning to teach and learn for semi-supervised few-shot image classification

• Main Authors: LI, Xinzhe, HUANG, Jianqiang, LIU, Yaoyao, ZHOU, Qin, ZHENG, Shibao, SCHIELE, Bernt, SUN, Qianru
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2021
• Subjects: Few-shot learning; Meta-learning; Semi-supervised learning; Databases and Information Systems; Graphics and Human Computer Interfaces
• Online Access: https://ink.library.smu.edu.sg/sis_research/6628; https://ink.library.smu.edu.sg/context/sis_research/article/7631/viewcontent/1_s20_S1077314221001144_main.pdf
• Institution: Singapore Management University

This paper presents a novel semi-supervised few-shot image classification method named Learning to Teach and Learn (LTTL) to effectively leverage unlabeled samples in small-data regimes. Our method is based on self-training, which assigns pseudo labels to unlabeled data. However, the conventional pseudo-labeling operation heavily relies on the initial model trained by using a handful of labeled data and may produce many noisy labeled samples. We propose to solve the problem with three steps: firstly, cherry-picking searches valuable samples from pseudo-labeled data by using a soft weighting network; and then, cross-teaching allows the classifiers to teach mutually for rejecting more noisy labels. A feature synthesizing strategy is introduced for cross-teaching to avoid clean samples being rejected by mistake; finally, the classifiers are fine-tuned with a few labeled data to avoid gradient drifts. We use the meta-learning paradigm to optimize the parameters in the whole framework. The proposed LTTL combines the power of meta-learning and self-training, achieving superior performance compared with the baseline methods on two public benchmarks.