Reinforced Attention for Few-Shot Learning and Beyond

Abstract

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.

References in corpus (19)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Prototypical Networks for Few-shot Learning
• Deep Residual Learning for Image Recognition
• Densely Connected Convolutional Networks
• Matching Networks for One Shot Learning
• SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learning
• Few-Shot Learning with Metric-Agnostic Conditional Embeddings
• Dynamic Few-Shot Visual Learning without Forgetting
• Learning an Adaptive Learning Rate Schedule
• End-to-end Learning of Action Detection from Frame Glimpses in Videos
• Negative Margin Matters: Understanding Margin in Few-shot Classification
• Geometric Back-projection Network for Point Cloud Classification
• When Does Self-supervision Improve Few-shot Learning?
• Deep Reinforcement Learning Attention Selection for Person Re-Identification
• Graph-based Interpolation of Feature Vectors for Accurate Few-Shot Classification
• Sim-Real Joint Reinforcement Transfer for 3D Indoor Navigation
• PoseAgent: Budget-Constrained 6D Object Pose Estimation via Reinforcement Learning