Reinforced Attention for Few-Shot Learning and Beyond

By Jie Hong, Pengfei Fang, Weihao Li, Tong Zhang, Christian Simon, Mehrtash Harandi, Lars Petersson. 2021

54 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

On Learning the Geodesic Path for Incremental Learning (2021, methodology): “In this line of work, there strategy is to only update some parameters in which it is common using dropout [37] and attention [16] for standard classification.”
Semantic-aware Knowledge Distillation for Few-Shot Class-Incremental Learning (2021, neutral): “There is another category, called dynamic few-shot learning (DFSL) [9, 27, 38, 12], which is similar to FSCIL.”