Mitigating Long-Tail Bias via Prompt-Controlled Diffusion Augmentation

ArXi:2602.04749v2 Announce Type: replace Long-tailed class imbalance remains a fundamental obstacle in semantic segmentation of high-resolution remote-sensing imagery, where dominant classes shape learned representations and rare classes are systematically under-segmented. This challenge becomes acute in cross-domain settings such as LoveDA, which exhibits an explicit Urban/Rural split with substantial appearance differences and inconsistent class-frequency statistics across domains.