{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/pp-liteseg-a-superior-real-time-semantic","title":"PP-LiteSeg: A Superior Real-Time Semantic Segmentation Model","arxiv_id":"2204.02681","date":"2022-04-06","proceeding":null,"authors":["Juncai Peng","Yi Liu","Shiyu Tang","Yuying Hao","Lutao Chu","Guowei Chen","Zewu Wu","Zeyu Chen","Zhiliang Yu","Yuning Du","Qingqing Dang","Baohua Lai","Qiwen Liu","Xiaoguang Hu","dianhai yu","Yanjun Ma"],"abstract":"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/273.6 FPS and 77.5% mIoU/102.6 FPS on NVIDIA GTX 1080Ti. Source code and models are available at PaddleSeg: https://github.com/PaddlePaddle/PaddleSeg.","url_abs":"https://arxiv.org/abs/2204.02681v1","url_pdf":"https://arxiv.org/pdf/2204.02681v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"pp-liteseg-a-superior-real-time-semantic","repo_url":"https://github.com/PaddlePaddle/PaddleSeg","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"paddle","reach":null},{"paper_slug":"pp-liteseg-a-superior-real-time-semantic","repo_url":"https://github.com/Deci-AI/super-gradients","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"pp-liteseg-a-superior-real-time-semantic","repo_url":"https://github.com/zh320/realtime-semantic-segmentation-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"real-time-semantic-segmentation","task_name":"Real-Time Semantic Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"pyramid-pooling-module","method_name":"Pyramid Pooling Module"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/real-time-semantic-segmentation-on-camvid","task":"Real-Time Semantic Segmentation","dataset":"CamVid","model":"PP-LiteSeg-B","rank_in_archive_order":12,"of":29,"metrics":{"Frame (fps)":"154.8","mIoU":"75"},"uses_additional_data":false},{"leaderboard":"/sota/real-time-semantic-segmentation-on-camvid","task":"Real-Time Semantic Segmentation","dataset":"CamVid","model":"PP-LiteSeg-T","rank_in_archive_order":16,"of":29,"metrics":{"Frame (fps)":"222.3","mIoU":"73.3"},"uses_additional_data":false},{"leaderboard":"/sota/real-time-semantic-segmentation-on-cityscapes","task":"Real-Time Semantic Segmentation","dataset":"Cityscapes test","model":"PP-LiteSeg-B2","rank_in_archive_order":6,"of":39,"metrics":{"Frame (fps)":"102.6(1080Ti)","mIoU":"77.5%"},"uses_additional_data":false},{"leaderboard":"/sota/real-time-semantic-segmentation-on-cityscapes","task":"Real-Time Semantic Segmentation","dataset":"Cityscapes test","model":"PP-LiteSeg-T2","rank_in_archive_order":16,"of":39,"metrics":{"Frame (fps)":"143.6(1080Ti)","mIoU":"74.9%"},"uses_additional_data":false},{"leaderboard":"/sota/real-time-semantic-segmentation-on-cityscapes","task":"Real-Time Semantic Segmentation","dataset":"Cityscapes test","model":"PP-LiteSeg-B1","rank_in_archive_order":20,"of":39,"metrics":{"Frame (fps)":"195.3(1080Ti)","mIoU":"73.9%"},"uses_additional_data":false},{"leaderboard":"/sota/real-time-semantic-segmentation-on-cityscapes","task":"Real-Time Semantic Segmentation","dataset":"Cityscapes test","model":"PP-LiteSeg-T1","rank_in_archive_order":24,"of":39,"metrics":{"Frame (fps)":"273.6(1080Ti)","mIoU":"72.0%"},"uses_additional_data":false},{"leaderboard":"/sota/real-time-semantic-segmentation-on-cityscapes-1","task":"Real-Time Semantic Segmentation","dataset":"Cityscapes val","model":"PP-LiteSeg-B2","rank_in_archive_order":9,"of":24,"metrics":{"mIoU":"78.2"},"uses_additional_data":false},{"leaderboard":"/sota/real-time-semantic-segmentation-on-cityscapes-1","task":"Real-Time Semantic Segmentation","dataset":"Cityscapes val","model":"PP-LiteSeg-T2","rank_in_archive_order":14,"of":24,"metrics":{"mIoU":"76"},"uses_additional_data":false},{"leaderboard":"/sota/real-time-semantic-segmentation-on-cityscapes-1","task":"Real-Time Semantic Segmentation","dataset":"Cityscapes val","model":"PP-LiteSeg-B1","rank_in_archive_order":17,"of":24,"metrics":{"mIoU":"75.3"},"uses_additional_data":false},{"leaderboard":"/sota/real-time-semantic-segmentation-on-cityscapes-1","task":"Real-Time Semantic Segmentation","dataset":"Cityscapes val","model":"PP-LiteSeg-T1","rank_in_archive_order":22,"of":24,"metrics":{"mIoU":"73.1"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2204.02681","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}