Abstract This paper introduces an extremely effificient CNN architecture named DFANet for semantic segmentation under resource constraints. Our proposed network starts from a single lightweight backbone and aggregates discriminative features through sub-network and sub-stage cascade respectively. Based on the multi-scale feature propagation, DFANet substantially reduces the number of parameters, but still obtains suffificient receptive fifield and enhances the model learning ability, which strikes a balance between the speed and segmentation performance. Experiments on Cityscapes and CamVid datasets demonstrate the superior performance of DFANet with 8× less FLOPs and 2× faster than the existing state-of-the-art real-time semantic segmentation methods while providing comparable accuracy. Specififically, it achieves 70.3% Mean IOU on the Cityscapes test dataset with only 1.7 GFLOPs and a speed of 160 FPS on one NVIDIA Titan X card, and 71.3% Mean IOU with 3.4 GFLOPs while inferring on a higher resolution image.