Papers › LiteSeg: A Novel Lightweight ConvNet for Semantic Segmentation

LiteSeg: A Novel Lightweight ConvNet for Semantic Segmentation

13 Dec 2019arXiv:1912.06683archive 2025-07-28

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 ×360 resolution on the Cityscapes dataset.

Paper PDF Code

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

tahaemara/LiteSeg mentioned on GitHubpytorch report

zh320/realtime-semantic-segmentation-pytorch mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Computational Efficiency Image Segmentation Medical Image Analysis Real-Time Semantic Segmentation Segmentation Semantic Segmentation

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Real-Time Semantic Segmentation	Cityscapes val	LiteSeg-MobileNet	mIoU	67.8%	#24 of 24	Archive leaderboard	report
Semantic Segmentation	Cityscapes test	LightSeg-DarkNet19	Category mIoU	88.29	#77 of 105	Archive leaderboard	report
Semantic Segmentation	Cityscapes test	LightSeg-DarkNet19	Mean IoU (class)	70.75%	#77 of 105	Archive leaderboard	report
Semantic Segmentation	Cityscapes test	LightSeg-MobileNet	Category mIoU	86.79	#85 of 105	Archive leaderboard	report
Semantic Segmentation	Cityscapes test	LightSeg-MobileNet	Mean IoU (class)	67.81%	#85 of 105	Archive leaderboard	report
Semantic Segmentation	Cityscapes test	LiteSeg-MobileNet	Mean IoU (class)	67.81%	#86 of 105	Archive leaderboard	report
Semantic Segmentation	Cityscapes test	LightSeg-ShuffleNet	Category mIoU	85.39	#96 of 105	Archive leaderboard	report
Semantic Segmentation	Cityscapes test	LightSeg-ShuffleNet	Mean IoU (class)	65.17%	#96 of 105	Archive leaderboard	report
Semantic Segmentation	Cityscapes test	LiteSeg-ShuffleNet	Mean IoU (class)	65.17%	#97 of 105	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Introduced by this paper: DASPP, LiteSeg

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections