Vision Transformers (ViTs) have shown success across a variety of tasks due to their ability to capture global image representations. Recent studies have identified the existence of high-norm tokens in ViTs, which can interfere with unsupervised object discovery. To address this, the use of "registers" which are additional tokens that isolate high norm patch tokens while capturing global image-level information has been proposed. While registers have been studied extensively for object discovery, their generalization properties particularly in out-of-distribution (OOD) scenarios, remains underexplored. In this paper, we examine the utility of register token embeddings in providing additional features for improving generalization and anomaly rejection. To that end, we propose a simple method that combines the special CLS token embedding commonly employed in ViTs with the average-pooled register embeddings to create feature representations which are subsequently used for training a downstream classifier. We find that this enhances OOD generalization and anomaly rejection, while maintaining in-distribution (ID) performance. Extensive experiments across multiple ViT backbones trained with and without registers reveal consistent improvements of 2-4\% in top-1 OOD accuracy and a 2-3\% reduction in false positive rates for anomaly detection. Importantly, these gains are achieved without additional computational overhead.

本文针对视觉变换器(ViTs)在无监督对象发现中因高范数token干扰而导致的泛化问题，提出了使用“寄存器”来隔离这些高范数token的方法。研究表明，结合寄存器嵌入与传统CLS token嵌入可以有效提高模型在分布外(OOD)场景下的泛化能力和异常检测的准确性，同时保持分布内(ID)性能，整体提升了2-4%的OOD准确率和2-3%的异常检测假阳性率。

在视觉变换器中利用寄存器实现强健适应