Few-shot-learning (FSL) commonly requires a model to identify images (queries) that belong to classes unseen during training, based on a few labelled samples of the new classes (support set) as reference. As the test classes are novel, FSL is challenging with high generalization error with respect to the novel classes, where outliers query or support image during inference exacerbate the error further. So far, plenty of algorithms involve training data augmentation to improve the generalization capability of FSL models. In contrast, inspired by the fact that test samples are more relevant to the target domain, we believe that test-time augmentation may be more useful than training augmentation for FSL. In this work, to reduce the bias caused by unconventional test samples, we generate new test samples through combining them with similar train-class samples. Averaged representations of the test-time augmentation are then considered for few-shot classification. According to our experiments, by augmenting the support set and query with a few additional generated sample, we can achieve improvement for trained FSL models. Importantly, our method is universally compatible with different off-the-shelf FSL models, whose performance can be improved without extra dataset nor further training of the models themselves. Codes are available at https://github.com/WendyBaiYunwei/FSL-Rectifier.
翻译:暂无翻译