DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation
This addresses the need for fast and accurate semantic segmentation in applications like autonomous driving, though it is incremental in optimizing existing architectures.
The paper tackles real-time semantic segmentation under resource constraints by proposing DFANet, an efficient CNN architecture that achieves 70.3% Mean IOU on Cityscapes with 1.7 GFLOPs and 160 FPS, offering 8x fewer FLOPs and 2x faster speed than prior methods.
This paper introduces an extremely efficient 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 sufficient receptive field 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$\times$ less FLOPs and 2$\times$ faster than the existing state-of-the-art real-time semantic segmentation methods while providing comparable accuracy. Specifically, 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.