In supervised learning, smoothing label/prediction distribution in neural network training has been proven useful in preventing the model from being over-confident, and is crucial for learning more robust visual representations. This observation motivates us to explore the way to make predictions flattened in unsupervised learning. Considering that human annotated labels are not adopted in unsupervised learning, we introduce a straightforward approach to perturb input image space in order to soften the output prediction space indirectly. Despite its conceptual simplicity, we show empirically that with the simple solution -- image mixture, we can learn more robust visual representations from the transformed input, and the benefits of representations learned from this space can be inherited by the linear classification and downstream tasks.

该论文提出了一种基于标签空间的无监督学习方法(Un-Mix)，通过混合输入数据进行联合工作，从而学习到更加精细、鲁棒且广义的表示。实验证明，在CIFAR-10、CIFAR-100、STL-10、Tiny ImageNet和ImageNet等数据集上，该方法均可以在保持基本方法的超参数和训练程序不变的条件下，显著提高模型的泛化性能。

Un-Mix: 重新思考无监督视觉表示学习中的图像混合