Self-supervised learning (SSL) has emerged as a central paradigm for training foundation models by leveraging large-scale unlabeled datasets, often producing representations with strong generalization capabilities. These models are typically pre-trained on general-purpose datasets such as ImageNet and subsequently adapted to various downstream tasks through finetuning. While prior work has investigated parameter-efficient adaptation methods like adapters, LoRA, and prompt tuning, primarily targeting downstream finetuning, extending the SSL pre-training itself in a continual manner to new domains under limited data remains largely underexplored, especially for downstream dense prediction tasks like semantic segmentation. In this work, we address the challenge of adapting vision foundation models to low-data target domains through continual self-supervised pre-training, specifically targeting downstream semantic segmentation. We propose GLARE (Global Local and Regional Enforcement), a novel continual self-supervised pre-training task designed to enhance downstream semantic segmentation performance. GLARE introduces patch-level augmentations to encourage local consistency and incorporates a regional consistency constraint that leverages spatial semantics in the data. For efficient continual pre-training, we initialize Vision Transformers (ViTs) with weights from existing SSL models and update only lightweight adapter modules specifically UniAdapter - while keeping the rest of the backbone frozen. Experiments across multiple semantic segmentation benchmarks on different domains demonstrate that GLARE consistently improves downstream performance with minimal computational and parameter overhead.

翻译：自监督学习（SSL）已成为利用大规模无标注数据集训练基础模型的核心范式，其产生的表征通常具备强大的泛化能力。这些模型通常在通用数据集（如ImageNet）上进行预训练，随后通过微调适配至各种下游任务。尽管先前研究已探索了参数高效的适配方法，如适配器、LoRA和提示调优，但这些方法主要针对下游微调阶段；而在有限数据条件下，以持续方式将SSL预训练本身扩展至新领域的研究仍相对不足，尤其对于语义分割等下游密集预测任务。本工作通过持续自监督预训练，针对下游语义分割任务，解决了视觉基础模型在低数据目标域中的适配挑战。我们提出了GLARE（全局局部与区域增强）——一种新颖的持续自监督预训练任务，旨在提升下游语义分割性能。GLARE引入图像块级数据增强以促进局部一致性，并结合利用数据空间语义的区域一致性约束。为实现高效持续预训练，我们采用现有SSL模型的权重初始化Vision Transformers（ViTs），并仅更新轻量级适配器模块（特别是UniAdapter），同时保持主干网络其余部分冻结。跨多个领域语义分割基准的实验表明，GLARE能以极小的计算与参数开销持续提升下游任务性能。