The recent rise of Self-Supervised Learning (SSL) as one of the preferred strategies for learning with limited labeled data, and abundant unlabeled data has led to the widespread use of these models. They are usually pretrained, finetuned, and evaluated on the same data distribution, i.e., within an in-distribution setting. However, they tend to perform poorly in out-of-distribution evaluation scenarios, a challenge that Unsupervised Domain Generalization (UDG) seeks to address. This paper introduces a novel method to standardize the styles of images in a batch. Batch styles standardization, relying on Fourier-based augmentations, promotes domain invariance in SSL by preventing spurious correlations from leaking into the features. The combination of batch styles standardization with the well-known contrastive-based method SimCLR leads to a novel UDG method named CLaSSy ($\textbf{C}$ontrastive $\textbf{L}$e$\textbf{a}$rning with $\textbf{S}$tandardized $\textbf{S}$t$\textbf{y}$les). CLaSSy offers serious advantages over prior methods, as it does not rely on domain labels and is scalable to handle a large number of domains. Experimental results on various UDG datasets demonstrate the superior performance of CLaSSy compared to existing UDG methods. Finally, the versatility of the proposed batch styles standardization is demonstrated by extending respectively the contrastive-based and non-contrastive-based SSL methods, SWaV and MSN, while considering different backbone architectures (convolutional-based, transformers-based).
翻译:最近自我强化学习(SSL)的兴起是使用有限标签数据学习的首选策略之一,而大量未贴标签数据则导致广泛使用这些模型。它们通常在相同的数据分布上,即在分配范围内,预先训练、微调和评估。然而,它们往往在分配外评价情景中表现不佳,这是无人监督的通用软件(UDG)寻求解决的挑战。本文引入了一种新颖的方法,将一组图像的风格标准化。批发风格标准化,依靠基于 Fourier 的增强,通过防止虚假的关联渗漏到功能中促进SLSL的域变异性。批发风格与众所周知的对比基础方法的组合导致一种新型的UDG方法,名为 ClaSSy (\ textb{C} 美元) 的内向基 $\ textflex{Lef} 的内置换式风格。 Snelliveferity{Slority{Slevority} 和LAx-deal-deal developyal rual_S frodal ladal lats ex lade laft laft laft lax_s lade lax lax_s lax_s lax lax dal_ lax dal_s lax lax lax lax lax lax lad fal_s_s_ lax fal lax lax lad frod fal lad frod frodald frod frod frod frod frod frod frod lad lads lads lads frods) lads) lads fal ladal ladal las) lads ladal ladal lads ladal ladal las lads lads las lad lad las las las las las las las las las las las las las las las la</s>