PP-LiteSeg: A Superior Real-Time Semantic Segmentation Model

04/06/2022
by   Juncai Peng, et al.
0

Real-world applications have high demands for semantic segmentation methods. Although semantic segmentation has made remarkable leap-forwards with deep learning, the performance of real-time methods is not satisfactory. In this work, we propose PP-LiteSeg, a novel lightweight model for the real-time semantic segmentation task. Specifically, we present a Flexible and Lightweight Decoder (FLD) to reduce computation overhead of previous decoder. To strengthen feature representations, we propose a Unified Attention Fusion Module (UAFM), which takes advantage of spatial and channel attention to produce a weight and then fuses the input features with the weight. Moreover, a Simple Pyramid Pooling Module (SPPM) is proposed to aggregate global context with low computation cost. Extensive evaluations demonstrate that PP-LiteSeg achieves a superior trade-off between accuracy and speed compared to other methods. On the Cityscapes test set, PP-LiteSeg achieves 72.0 mIoU/102.6 FPS on NVIDIA GTX 1080Ti. Source code and models are available at PaddleSeg: https://github.com/PaddlePaddle/PaddleSeg.

READ FULL TEXT

page 2

page 7

research
06/15/2022

S^2-FPN: Scale-ware Strip Attention Guided Feature Pyramid Network for Real-time Semantic Segmentation

Modern high-performance semantic segmentation methods employ a heavy bac...
research
06/04/2023

Cross-CBAM: A Lightweight network for Scene Segmentation

Scene parsing is a great challenge for real-time semantic segmentation. ...
research
05/27/2021

Feature Reuse and Fusion for Real-time Semantic segmentation

For real-time semantic segmentation, how to increase the speed while mai...
research
10/22/2021

Reimagine BiSeNet for Real-Time Domain Adaptation in Semantic Segmentation

Semantic segmentation models have reached remarkable performance across ...
research
02/21/2023

Lightweight Real-time Semantic Segmentation Network with Efficient Transformer and CNN

In the past decade, convolutional neural networks (CNNs) have shown prom...
research
03/26/2023

You Only Segment Once: Towards Real-Time Panoptic Segmentation

In this paper, we propose YOSO, a real-time panoptic segmentation framew...
research
01/11/2023

Head-Free Lightweight Semantic Segmentation with Linear Transformer

Existing semantic segmentation works have been mainly focused on designi...

Please sign up or login with your details

Forgot password? Click here to reset