Reinforced Attention for Few-Shot Learning and Beyond
This work addresses the problem of improving representation learning for few-shot classification, which is incremental as it builds on existing attention and reinforcement learning methods.
The paper tackles few-shot learning by introducing an attention agent trained with reinforcement learning to adaptively localize representative regions on feature maps, resulting in more discriminative representations and showing effectiveness in image classification tasks.
Few-shot learning aims to correctly recognize query samples from unseen classes given a limited number of support samples, often by relying on global embeddings of images. In this paper, we propose to equip the backbone network with an attention agent, which is trained by reinforcement learning. The policy gradient algorithm is employed to train the agent towards adaptively localizing the representative regions on feature maps over time. We further design a reward function based on the prediction of the held-out data, thus helping the attention mechanism to generalize better across the unseen classes. The extensive experiments show, with the help of the reinforced attention, that our embedding network has the capability to progressively generate a more discriminative representation in few-shot learning. Moreover, experiments on the task of image classification also show the effectiveness of the proposed design.