Contextual Gradient Scaling for Few-Shot Learning

TL;DR

This paper introduces CxGrad, a method that scales backbone gradients in MAML to improve task-specific learning, significantly enhancing few-shot classification performance across domains.

Contribution

The paper proposes contextual gradient scaling (CxGrad), a novel approach to adjust backbone gradient norms in MAML for better task adaptation.

Findings

CxGrad improves MAML performance in few-shot classification.

It enhances task-specific feature learning in the backbone.

Results show significant gains in both same- and cross-domain tasks.

Abstract

Model-agnostic meta-learning (MAML) is a well-known optimization-based meta-learning algorithm that works well in various computer vision tasks, e.g., few-shot classification. MAML is to learn an initialization so that a model can adapt to a new task in a few steps. However, since the gradient norm of a classifier (head) is much bigger than those of backbone layers, the model focuses on learning the decision boundary of the classifier with similar representations. Furthermore, gradient norms of high-level layers are small than those of the other layers. So, the backbone of MAML usually learns task-generic features, which results in deteriorated adaptation performance in the inner-loop. To resolve or mitigate this problem, we propose contextual gradient scaling (CxGrad), which scales gradient norms of the backbone to facilitate learning task-specific knowledge in the inner-loop. Since the scaling factors are generated from task-conditioned parameters, gradient norms of the backbone can be scaled in a task-wise fashion. Experimental results show that CxGrad effectively encourages the backbone to learn task-specific knowledge in the inner-loop and improves the performance of MAML up to a significant margin in both same- and cross-domain few-shot classification.