RTFormer: Efficient Design for Real-Time Semantic Segmentation with Transformer Reference Wang, Jian, Chenhui Gou, Qiman Wu, Haocheng Feng, Junyu Han, Errui Ding, and Jingdong Wang. "RTFormer: Efficient Design for Real-Time Semantic Segmentation with Transformer." arXiv preprint arXiv:2210.07124 (2022). Performance Cityscapes Model Backbone Resolution Training Iters mIoU mIoU (flip) mIoU (ms+flip) Links RTFormer-Base - 1024x512 120000 79.24% 79.80% 80.48% model | log | vdl RTFormer-Slim - 1024x512 120000 76.31% 77.05% 77.91% model | log | vdl ADE20k Model Backbone Resolution Training Iters mIoU mIoU (flip) mIoU (ms+flip) Links RTFormer-Base - 512x512 160000 42.02% 42.43% 42.97% model | log | vdl RTFormer-Slim - 512x512 160000 36.67% 37.32% 37.58% model | log | vdl