Self-supervised Learning (SSL) aims to learn transferable feature representations for downstream applications without relying on labeled data. The Barlow Twins algorithm, renowned for its widespread adoption and straightforward implementation compared to its counterparts like contrastive learning methods, minimizes feature redundancy while maximizing invariance to common corruptions. Optimizing for the above objective forces the network to learn useful representations, while avoiding noisy or constant features, resulting in improved downstream task performance with limited adaptation. Despite Barlow Twins' proven effectiveness in pre-training, the underlying SSL objective can inadvertently cause feature overfitting due to the lack of strong interaction between the samples unlike the contrastive learning approaches. From our experiments, we observe that optimizing for the Barlow Twins objective doesn't necessarily guarantee sustained improvements in representation quality beyond a certain pre-training phase, and can potentially degrade downstream performance on some datasets. To address this challenge, we introduce Mixed Barlow Twins, which aims to improve sample interaction during Barlow Twins training via linearly interpolated samples. This results in an additional regularization term to the original Barlow Twins objective, assuming linear interpolation in the input space translates to linearly interpolated features in the feature space. Pre-training with this regularization effectively mitigates feature overfitting and further enhances the downstream performance on CIFAR-10, CIFAR-100, TinyImageNet, STL-10, and ImageNet datasets. The code and checkpoints are available at: https://github.com/wgcban/mix-bt.git

翻译：自监督学习（SSL）旨在无需依赖标注数据，为下游应用学习可迁移的特征表示。与对比学习等方法相比，Barlow Twins算法因其广泛采用和简洁实现而闻名，它在最小化特征冗余的同时最大化对常见扰动的不变性。通过优化上述目标，网络被迫学习有用表示，同时避免噪声或恒定特征，从而在有限适配下提升下游任务性能。尽管Barlow Twins在预训练中已证实有效，但其底层SSL目标因缺乏样本间的强交互（与对比学习方法不同），可能无意中导致特征过拟合。从我们的实验中观察到，优化Barlow Twins目标并不一定保证超过特定预训练阶段的表示质量持续提升，且可能在某些数据集上降低下游性能。为解决该挑战，我们提出混合Barlow Twins方法，旨在通过线性插值样本改进Barlow Twins训练中的样本交互。这在原始Barlow Twins目标中引入额外正则化项，假设输入空间的线性插值会转化为特征空间的线性插值特征。采用该正则化进行预训练可有效缓解特征过拟合，并在CIFAR-10、CIFAR-100、TinyImageNet、STL-10及ImageNet数据集上进一步提升下游性能。代码与检查点可访问：https://github.com/wgcban/mix-bt.git