Abstract
Recent advances in self-supervised learning (SSL) have made it possible to learn general-purpose visual features that capture both the high-level semantics and the fine-grained spatial structure of images. Most notably, the recent DINOv2 has established a new state of the art by surpassing weakly supervised methods (WSL) like OpenCLIP on most benchmarks. In this survey, we examine the core ideas behind its approach, multi-crop view augmentation and self-distillation with a mean teacher, and trace their development in previous work. We then compare the performance of DINO and DINOv2 with other SSL and WSL methods across various downstream tasks, and highlight some remarkable emergent properties of their learned features with transformer backbones. We conclude by briefly discussing DINOv2's limitations, its impact, and future research directions.
Abstract (translated)
最近的自监督学习（SSL）进展使得能够学习到既捕捉图像高层语义又包含细微空间结构的一般视觉特征成为可能。尤为值得注意的是，近期推出的DINOv2通过在大多数基准测试中超越弱监督方法（WSL），如OpenCLIP，确立了新的性能标准。在这份综述中，我们将探讨其核心理念——多视角增强和带有均值教师的自我蒸馏，并追溯这些概念在先前工作中的发展。接着，我们将在各种下游任务上比较DINO与DINOv2和其他SSL及WSL方法的表现，并强调它们使用变换器（Transformer）作为骨干网络时学习到的一些显著特性。最后，我们将简要讨论DINOv2的局限性、其影响以及未来的研究方向。
URL
https://arxiv.org/abs/2510.03606
