Stronger, Fewer, Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentation
CVPR 2024(2023)
摘要
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
backbone, Rein achieves a mIoU of 68.1
any real urban-scene datasets.Code is available at
https://github.com/w1oves/Rein.git.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要