# LiteSeg: A Novel Lightweight ConvNet for Semantic Segmentation

arXiv: https://arxiv.org/abs/1912.06683 · HTML: https://mlsanity.com/paper/1912.06683/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Dec 2019.

## Built on by (most cited first, 13 of 13)

- [AttaNet: Attention-Augmented Network for Fast and Accurate Scene Parsing](https://mlsanity.com/paper/2103.05930/) (2021)
- [Efficient Joint-Dimensional Search with Solution Space Regularization for Real-Time Semantic Segmentation](https://mlsanity.com/paper/2208.05271/) (2022)
- [Enabling Resource-efficient AIoT System with Cross-level Optimization: A survey](https://mlsanity.com/paper/2309.15467/) (2023)
- [Semantic Scene Segmentation for Robotics Applications](https://mlsanity.com/paper/2108.11128/) (2021)
- [Real-Time Monocular Human Depth Estimation and Segmentation on Embedded Systems](https://mlsanity.com/paper/2108.10506/) (2021)
- [L^3U-net: Low-Latency Lightweight U-net Based Image Segmentation Model for Parallel CNN Processors](https://mlsanity.com/paper/2203.16528/) (2022)
- [A Threefold Review on Deep Semantic Segmentation: Efficiency-oriented, Temporal and Depth-aware design](https://mlsanity.com/paper/2303.04315/) (2023)
- [Cross-CBAM: A Lightweight network for Scene Segmentation](https://mlsanity.com/paper/2306.02306/) (2023)
- [Rethinking Intermediate Layers design in Knowledge Distillation for Kidney and Liver Tumor Segmentation](https://mlsanity.com/paper/2311.16700/) (2023)
- [DPANET:Dual Pooling Attention Network for Semantic Segmentation](https://mlsanity.com/paper/2210.05437/) (2022)
- [Tree-NET: Enhancing 2D Medical Image Segmentation Through Efficient Low-Level Feature Training](https://mlsanity.com/paper/2501.02140/) (2025)
- [Enhancing Shape Perception and Segmentation Consistency for Industrial Image Inspection](https://mlsanity.com/paper/2505.14718/) (2025)
- [AVOID: The Adverse Visual Conditions Dataset with Obstacles for Driving Scene Understanding](https://mlsanity.com/paper/2512.23215/) (2025)

## Abstract (arXiv)

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.