Abstract | ||
---|---|---|
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. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1016/j.cviu.2021.103270 | Computer Vision and Image Understanding |
Keywords | DocType | Volume |
41A05,41A10,65D05,65D17 | Journal | 212 |
Issue | ISSN | Citations |
1 | 1077-3142 | 0 |
PageRank | References | Authors |
0.34 | 8 | 7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xinzhe Li | 1 | 14 | 3.67 |
Jianqiang Huang | 2 | 55 | 19.18 |
Yaoyao Liu | 3 | 52 | 3.88 |
Qin Zhou | 4 | 0 | 1.01 |
Shibao Zheng | 5 | 214 | 30.64 |
Bernt Schiele | 6 | 12901 | 971.29 |
Sun Qianru | 7 | 227 | 19.41 |