PAT: Pixel-wise Adaptive Training for Robust Long-tailed Semantic Segmentation

The core message of this article is to introduce Pixel-wise Adaptive Training (PAT), a novel approach for addressing long-tailed rare category problems in semantic segmentation. PAT comprises two key contributions: class-wise gradient magnitude homogenization and pixel-wise class-specific loss adaptation, which effectively alleviate the imbalance among class-specific predictions and the detrimental impact of rare classes within the long-tailed distribution.