LiteSeg: A Novel Lightweight ConvNet for Semantic Segmentation

13 Dec 2019  ·  Taha Emara, Hossam E. Abd El Munim, Hazem M. Abbas ·

Semantic image segmentation plays a pivotal role in many vision applications including autonomous driving and medical image analysis. Most of the former approaches move towards enhancing the performance in terms of accuracy with a little awareness of computational efficiency... In this paper, we introduce LiteSeg, a lightweight architecture for semantic image segmentation. In this work, we explore a new deeper version of Atrous Spatial Pyramid Pooling module (ASPP) and apply short and long residual connections, and depthwise separable convolution, resulting in a faster and efficient model. LiteSeg architecture is introduced and tested with multiple backbone networks as Darknet19, MobileNet, and ShuffleNet to provide multiple trade-offs between accuracy and computational cost. The proposed model LiteSeg, with MobileNetV2 as a backbone network, achieves an accuracy of 67.81% mean intersection over union at 161 frames per second with $640 \times 360$ resolution on the Cityscapes dataset. read more

PDF Abstract


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Semantic Segmentation Cityscapes test LightSeg-DarkNet19 Mean IoU (class) 70.75% # 63
GFlops 103.09 # 3
Category mIoU 88.29 # 1
Semantic Segmentation Cityscapes test LiteSeg-MobileNet Mean IoU (class) 67.81% # 71
Semantic Segmentation Cityscapes test LightSeg-MobileNet Mean IoU (class) 67.81% # 71
GFlops 4.9 # 2
Category mIoU 86.79 # 2
Semantic Segmentation Cityscapes test LightSeg-ShuffleNet Mean IoU (class) 65.17% # 81
GFlops 2.75 # 1
Category mIoU 85.39 # 3
Semantic Segmentation Cityscapes test LiteSeg-ShuffleNet Mean IoU (class) 65.17% # 81
Real-Time Semantic Segmentation Cityscapes val LiteSeg-MobileNet mIoU 67.8% # 1