用混合样本防止Barlow Twins过拟合
Guarding Barlow Twins Against Overfitting with Mixed Samples
AI总结：
本文提出Mixed Barlow Twins方法，通过线性插值样本增强样本交互并引入额外正则化项，缓解Barlow Twins自监督预训练中的特征过拟合问题，从而提升多个图像数据集上的下游性能。
摘要：
自监督学习（SSL）旨在不依赖标注数据的情况下，为下游应用学习可迁移的特征表示。Barlow Twins算法因其广泛采用且实现比对比学习方法等同类算法更简单而闻名，它在最大化对常见扰动的不变性的同时最小化特征冗余。优化上述目标迫使网络学习有用的表示，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在预训练中已被证明有效，但由于样本之间缺乏像对比学习方法那样的强交互，其底层SSL目标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目标并不一定能在某个预训练阶段之后保证表示质量的持续提升，并且可能在某些数据集上降低下游性能。为应对这一挑战，我们提出Mixed Barlow Twins，旨在通过线性插值样本改善Barlow Twins训练过程中的样本交互。这在原始Barlow Twins目标上增加了一个额外的正则化项，假设输入空间中的线性插值会转化为特征空间中的线性插值特征。使用该正则化进行预训练可有效缓解特征过拟合，并进一步提升在CIFAR-10、CIFAR-100、TinyImageNet、STL-10和ImageNet数据集上的下游性能。代码和检查点可在以下地址获取：https://github.com/wgcban/mix-bt.git
英文摘要：
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
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
