Stronger, Fewer, & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentation

In this paper, we first assess and harness various Vision Foundation Models (VFMs) in the context of Domain Generalized Semantic Segmentation (DGSS). Driven by the motivation that Leveraging Stronger pre-trained models and Fewer trainable parameters for Superior generalizability, we introduce a robust fine-tuning approach, namely Rein, to parameter-efficiently harness VFMs for DGSS. Built upon a set of trainable tokens, each linked to distinct instances, Rein precisely refines and forwards the feature maps from each layer to the next layer within the backbone. This process produces diverse refinements for different categories within a single image. With fewer trainable parameters, Rein efficiently fine-tunes VFMs for DGSS tasks, surprisingly surpassing full parameter fine-tuning. Extensive experiments across various settings demonstrate that Rein significantly outperforms state-of-the-art methods. Remarkably, with just an extra 1% of trainable parameters within the frozen backbone, Rein achieves a mIoU of 78.4% on the Cityscapes, without accessing any real urban-scene datasets.Code is available at

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Domain Adaptation Cityscapes to ACDC Rein mIoU 77.6 # 1
Domain Generalization GTA5-to-Cityscapes Rein mIoU 64.3 # 2
Domain Generalization GTA-to-Avg(Cityscapes,BDD,Mapillary) Rein mIoU 64.3 # 1
Domain Adaptation GTAV to Cityscapes+Mapillary Rein mIoU 63.3 # 1


No methods listed for this paper. Add relevant methods here