Reinforced Attention for Few-Shot Learning and Beyond

Jie Hong, Pengfei Fang, Weihao Li, Tong Zhang, Christian Simon, Mehrtash Harandi, Lars Petersson; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, pp. 913-923


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.

Related Material

[pdf] [supp] [arXiv]
@InProceedings{Hong_2021_CVPR, author = {Hong, Jie and Fang, Pengfei and Li, Weihao and Zhang, Tong and Simon, Christian and Harandi, Mehrtash and Petersson, Lars}, title = {Reinforced Attention for Few-Shot Learning and Beyond}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2021}, pages = {913-923} }