# Learning from Adversarial Features for Few-Shot Classification

arXiv: https://arxiv.org/abs/1903.10225 · HTML: https://mlsanity.com/paper/1903.10225/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Mar 2019.

## Built on by (most cited first, 3 of 3)

- [StyleAdv: Meta Style Adversarial Training for Cross-Domain Few-Shot Learning](https://mlsanity.com/paper/2302.09309/) (2023)
- [MetaCLBench: Meta Continual Learning Benchmark on Resource-Constrained Edge Devices](https://mlsanity.com/paper/2504.00174/) (2025)
- [Hyperbolic Coarse-to-Fine Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2509.18504/) (2025)

## Abstract (arXiv)

Many recent few-shot learning methods concentrate on designing novel model architectures. In this paper, we instead show that with a simple backbone convolutional network we can even surpass state-of-the-art classification accuracy. The essential part that contributes to this superior performance is an adversarial feature learning strategy that improves the generalization capability of our model. In this work, adversarial features are those features that can cause the classifier uncertain about its prediction. In order to generate adversarial features, we firstly locate adversarial regions based on the derivative of the entropy with respect to an averaging mask. Then we use the adversarial region attention to aggregate the feature maps to obtain the adversarial features. In this way, we can explore and exploit the entire spatial area of the feature maps to mine more diverse discriminative knowledge. We perform extensive model evaluations and analyses on miniImageNet and tieredImageNet datasets demonstrating the effectiveness of the proposed method.