搞语义分割的可以试试这个，它只增强模型犯难的区域，在几个自动驾驶数据集上提点挺明显，尤其是稀有类别。
该论文提出一种不确定性引导的合成上下文增强策略，利用基线分割器的预测熵识别不确定语义区域，仅对互补视觉上下文进行修补。在Cityscapes、UAVID和BDD100K数据集上，微调后mIoU分别提升1.2%、2.1%和1.8%，尤其在公交车、火车和汽车等稀有类别上增益最大。该方法无需外部模型，严格保持标签有效性，且计算损失时仅基于原始像素。
Preserve the Hard, Regenerate the Rest: Uncertainty-Guided Synthetic Training Data Augmentation with Diffusion Models
Semantic segmentation models struggle with data sparsity and rare or visually diverse regions, e.g., dense regions or small objects in aerial or autonomous mobility data. While synthetic augmentation is an appealing solution, directly generating new labeled data risks misalignment of labels and generated pixels. Existing solutions to this problem often rely on external models, or employ coarse heuristics such as indiscriminately augmenting all foreground objects or entire backgrounds, which wastes capacity on uninformative pixels. To address this, we propose an uncertainty-guided synthetic context augmentation strategy that strictly preserves label validity and efficiently maximizes pixel informativeness per synthetic sample - no external guardrails required. Using a baseline segmenter's predictive entropy, we identify uncertain semantic regions and inpaint only the complementary visual context. When fine-tuning the segmenter on this synthetic data, we compute the loss only over the original pixels, excluding inpainted regions. This focuses learning on the unmodified, uncertain regions while presenting them in novel contexts. We demonstrate substantial mIoU gains on Cityscapes, UAVID, and BDD100K with the largest gains on rare and difficult classes such as buses, trains, or (from the aerial perspective) cars. Our results demonstrate that uncertainty-guided context augmentation is a highly effective lever to improve segmentation performance on complex datasets, with code provided at https://github.com/XITASO/Preserve-the-Hard-Regenerate-the-Rest.