用DINOv2加简单解码器，轻松提升语义分割鲁棒性。
First Place Solution to the ECCV 2024 BRAVO Challenge: Evaluating Robustness of Vision Foundation Models for Semantic Segmentation
- 在DINOv2后接轻量解码器，全模型微调
- 在多个分布外数据集上超越复杂方法，夺冠
- 适合关注视觉基础模型鲁棒性的研究者
本文报告了在ECCV 2024 BRAVO挑战赛中获得第一名的解决方案。该模型在Cityscapes数据集上训练，其鲁棒性在多个分布外数据集上进行评估。我们的方法通过在DINOv2基础上附加一个简单的分割解码器，并对整个模型进行微调，利用视觉基础模型强大的表征能力。该方法在性能上优于更复杂的现有方法，在挑战赛中取得第一名。代码已公开：https://github.com/tue-mps/benchmark-vfm-ss。
原文摘要 · Abstract (English)
In this report, we present the first place solution to the ECCV 2024 BRAVO Challenge, where a model is trained on Cityscapes and its robustness is evaluated on several out-of-distribution datasets. Our solution leverages the powerful representations learned by vision foundation models, by attaching a simple segmentation decoder to DINOv2 and fine-tuning the entire model. This approach outperforms more complex existing approaches, and achieves first place in the challenge. Our code is publicly available at https://github.com/tue-mps/benchmark-vfm-ss.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。