DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation

Abstract

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.

References in corpus (3)

• Rethinking Atrous Convolution for Semantic Image Segmentation
• Recurrent Models of Visual Attention
• Real-time Semantic Image Segmentation via Spatial Sparsity

Cited by in corpus (6)

• Real-Time Semantic Segmentation via Multiply Spatial Fusion Network
• EXTD: Extremely Tiny Face Detector via Iterative Filter Reuse
• Temporally Distributed Networks for Fast Video Semantic Segmentation
• Robust Semantic Segmentation with Superpixel-Mix
• ELKPPNet: An Edge-aware Neural Network with Large Kernel Pyramid Pooling for Learning Discriminative Features in Semantic Segmentation
• A De-raining semantic segmentation network for real-time foreground segmentation