AutoMix: Unveiling the Power of Mixup for Stronger Classifiers

Data mixing augmentation have proved to be effective in improving the generalization ability of deep neural networks. While early methods mix samples by hand-crafted policies (e.g., linear interpolation), recent methods utilize saliency information to match the mixed samples and labels via complex offline optimization. However, there arises a trade-off between precise mixing policies and optimization complexity. To address this challenge, we propose a novel automatic mixup (AutoMix) framework, where the mixup policy is parameterized and serves the ultimate classification goal directly. Specifically, AutoMix reformulates the mixup classification into two sub-tasks (i.e., mixed sample generation and mixup classification) with corresponding sub-networks and solves them in a bi-level optimization framework. For the generation, a learnable lightweight mixup generator, Mix Block, is designed to generate mixed samples by modeling patch-wise relationships under the direct supervision of the corresponding mixed labels. To prevent the degradation and instability of bi-level optimization, we further introduce a momentum pipeline to train AutoMix in an end-to-end manner. Extensive experiments on nine image benchmarks prove the superiority of AutoMix compared with state-of-the-arts in various classification scenarios and downstream tasks.

We will update configs and models (ResNets, ViTs, Swin-T, and ConvNeXt-T) for AutoMix soon (please contact us if you want the models right now). Please refer to Model Zoo for image classification results.

@InProceedings{liu2022automix,
      title={AutoMix: Unveiling the Power of Mixup for Stronger Classifiers},
      author={Zicheng Liu and Siyuan Li and Di Wu and Zhiyuan Chen and Lirong Wu and Jianzhu Guo and Stan Z. Li},
      booktitle={European Conference on Computer Vision (ECCV)},
      pages={441--458},
      year={2022},
}