MixStyle Neural Networks for Domain Generalization and Adaptation

Abstract

Neural networks do not generalize well to unseen data with domain shifts -- a longstanding problem in machine learning and AI. To overcome the problem, we propose MixStyle, a simple plug-and-play, parameter-free module that can improve domain generalization performance without the need to collect more data or increase model capacity. The design of MixStyle is simple: it mixes the feature statistics of two random instances in a single forward pass during training. The idea is grounded by the finding from recent style transfer research that feature statistics capture image style information, which essentially defines visual domains. Therefore, mixing feature statistics can be seen as an efficient way to synthesize new domains in the feature space, thus achieving data augmentation. MixStyle is easy to implement with a few lines of code, does not require modification to training objectives, and can fit a variety of learning paradigms including supervised domain generalization, semi-supervised domain generalization, and unsupervised domain adaptation. Our experiments show that MixStyle can significantly boost out-of-distribution generalization performance across a wide range of tasks including image recognition, instance retrieval and reinforcement learning.

arXiv commentExtension of https://openreview.net/forum?id=6xHJ37MVxxp. Code available at https://github.com/KaiyangZhou/mixstyle-release. To appear in IJCV

References in corpus (27)

• Playing Atari with Deep Reinforcement Learning
• mixup: Beyond Empirical Risk Minimization
• Instance Normalization: The Missing Ingredient for Fast Stylization
• Learning Transferable Features with Deep Adaptation Networks
• Improved Regularization of Convolutional Neural Networks with Cutout
• SGDR: Stochastic Gradient Descent with Warm Restarts
• DARTS: Differentiable Architecture Search
• A Learned Representation For Artistic Style
• Domain Generalization via Invariant Feature Representation
• VisDA: The Visual Domain Adaptation Challenge
• IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
• DropBlock: A regularization method for convolutional networks
• Manifold Mixup: Better Representations by Interpolating Hidden States
• Generalizing Across Domains via Cross-Gradient Training
• A Study on Overfitting in Deep Reinforcement Learning
• Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World
• Quantifying Generalization in Reinforcement Learning
• Illuminating Generalization in Deep Reinforcement Learning through Procedural Level Generation
• Torchreid: A Library for Deep Learning Person Re-Identification in Pytorch
• Generalization and Regularization in DQN
• Transfer Learning for Related Reinforcement Learning Tasks via Image-to-Image Translation
• Generalization in Reinforcement Learning with Selective Noise Injection and Information Bottleneck
• Learning Generalisable Omni-Scale Representations for Person Re-Identification
• Domain Generalization with MixStyle
• Episodic Training for Domain Generalization
• Cluster Alignment with a Teacher for Unsupervised Domain Adaptation
• Semi-Supervised Domain Generalization with Stochastic StyleMatch