{"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/liteseg-a-novel-lightweight-convnet-for","title":"LiteSeg: A Novel Lightweight ConvNet for Semantic Segmentation","arxiv_id":"1912.06683","date":"2019-12-13","proceeding":null,"authors":["Taha Emara","Hossam E. Abd El Munim","Hazem M. Abbas"],"abstract":"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.","url_abs":"https://arxiv.org/abs/1912.06683v1","url_pdf":"https://arxiv.org/pdf/1912.06683v1.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":"liteseg-a-novel-lightweight-convnet-for","repo_url":"https://github.com/tahaemara/LiteSeg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"liteseg-a-novel-lightweight-convnet-for","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":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"medical-image-analysis","task_name":"Medical Image Analysis"},{"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":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"channel-shuffle","method_name":"Channel Shuffle"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"daspp","method_name":"DASPP"},{"method_slug":"darknet-19","method_name":"Darknet-19"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"depthwise-convolution","method_name":"Depthwise Convolution"},{"method_slug":"depthwise-separable-convolution","method_name":"Depthwise Separable Convolution"},{"method_slug":"dilated-convolution","method_name":"Dilated Convolution"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"grouped-convolution","method_name":"Grouped Convolution"},{"method_slug":"groupwise-point-convolution","method_name":"Groupwise Point Convolution"},{"method_slug":"inverted-residual-block","method_name":"Inverted Residual Block"},{"method_slug":"liteseg","method_name":"LiteSeg"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"nesterov-accelerated-gradient","method_name":"Nesterov Accelerated Gradient"},{"method_slug":"pointwise-convolution","method_name":"Pointwise Convolution"},{"method_slug":"polynomial-rate-decay","method_name":"Polynomial Rate Decay"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"shufflenet","method_name":"ShuffleNet"},{"method_slug":"shufflenet-block","method_name":"ShuffleNet Block"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"spatial-pyramid-pooling","method_name":"Spatial Pyramid Pooling"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[{"slug":"daspp","name":"DASPP","full_name":"Deeper Atrous Spatial Pyramid Pooling"},{"slug":"liteseg","name":"LiteSeg","full_name":"LiteSeg"}],"results":[{"leaderboard":"/sota/real-time-semantic-segmentation-on-cityscapes-1","task":"Real-Time Semantic Segmentation","dataset":"Cityscapes val","model":"LiteSeg-MobileNet","rank_in_archive_order":24,"of":24,"metrics":{"mIoU":"67.8%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-cityscapes","task":"Semantic Segmentation","dataset":"Cityscapes test","model":"LightSeg-DarkNet19","rank_in_archive_order":77,"of":105,"metrics":{"Category mIoU":"88.29","Mean IoU (class)":"70.75%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-cityscapes","task":"Semantic Segmentation","dataset":"Cityscapes test","model":"LightSeg-MobileNet","rank_in_archive_order":85,"of":105,"metrics":{"Category mIoU":"86.79","Mean IoU (class)":"67.81%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-cityscapes","task":"Semantic Segmentation","dataset":"Cityscapes test","model":"LiteSeg-MobileNet","rank_in_archive_order":86,"of":105,"metrics":{"Mean IoU (class)":"67.81%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-cityscapes","task":"Semantic Segmentation","dataset":"Cityscapes test","model":"LightSeg-ShuffleNet","rank_in_archive_order":96,"of":105,"metrics":{"Category mIoU":"85.39","Mean IoU (class)":"65.17%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-cityscapes","task":"Semantic Segmentation","dataset":"Cityscapes test","model":"LiteSeg-ShuffleNet","rank_in_archive_order":97,"of":105,"metrics":{"Mean IoU (class)":"65.17%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1912.06683","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}