Augmented domain agreement for adaptable Meta-Learner on Few-Shot classification

摘要

Meta-learning approaches are recently introduced to obtain a proficient model in the problem of few-shot learning. The existing state-of-the-art methods can resolve the training difficulty to achieve the model generalization with limited instances by incorporating several tasks containing various drawn classes. However, during the fast-adaptation stage, the characteristics of instances in meta-training and meta-test sets are assumed to be similar. In contrast, most meta-learning algorithms are implemented in challenging settings where those are drawn from different populations. This critical assumption can cause the model to exhibit degraded performance. We propose an Augmented Domain Agreement for Adaptable Meta-Learner (AD2AML), which augments the domain adaptation framework in meta-learning to overcome this problem. We minimize the latent representation divergence of the inputs drawn from different distributions to enhance the model at obtaining more general features. Therefore, the trained network can be more transferable at shifted domain conditions. Furthermore, we extend our main idea by augmenting the image reconstruction network with cross-consistency loss to encourage the shared network to extract a similar input representation. We demonstrate our proposed method’s effectiveness on the benchmark datasets of few-shot classification and few-shot domain adaptation problems. Our experiment shows that our proposed idea can improve generalization performance. Moreover, the extension with image reconstruction and cross-consistency loss can stabilize domain loss minimization during training.