{"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/swinmtl-a-shared-architecture-for","title":"SwinMTL: A Shared Architecture for Simultaneous Depth Estimation and Semantic Segmentation from Monocular Camera Images","arxiv_id":"2403.10662","date":"2024-03-15","proceeding":null,"authors":["Pardis Taghavi","Reza Langari","Gaurav Pandey"],"abstract":"This research paper presents an innovative multi-task learning framework that allows concurrent depth estimation and semantic segmentation using a single camera. The proposed approach is based on a shared encoder-decoder architecture, which integrates various techniques to improve the accuracy of the depth estimation and semantic segmentation task without compromising computational efficiency. Additionally, the paper incorporates an adversarial training component, employing a Wasserstein GAN framework with a critic network, to refine model's predictions. The framework is thoroughly evaluated on two datasets - the outdoor Cityscapes dataset and the indoor NYU Depth V2 dataset - and it outperforms existing state-of-the-art methods in both segmentation and depth estimation tasks. We also conducted ablation studies to analyze the contributions of different components, including pre-training strategies, the inclusion of critics, the use of logarithmic depth scaling, and advanced image augmentations, to provide a better understanding of the proposed framework. The accompanying source code is accessible at \\url{https://github.com/PardisTaghavi/SwinMTL}.","url_abs":"https://arxiv.org/abs/2403.10662v1","url_pdf":"https://arxiv.org/pdf/2403.10662v1.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":"swinmtl-a-shared-architecture-for","repo_url":"https://github.com/pardistaghavi/swinmtl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"monocular-depth-estimation","task_name":"Monocular Depth Estimation"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"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":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/depth-estimation-on-cityscapes-test","task":"Depth Estimation","dataset":"Cityscapes test","model":"SwinMTL","rank_in_archive_order":1,"of":2,"metrics":{"RMSE":"6.352"},"uses_additional_data":false},{"leaderboard":"/sota/monocular-depth-estimation-on-cityscapes","task":"Monocular Depth Estimation","dataset":"Cityscapes","model":"SwinMTL","rank_in_archive_order":1,"of":3,"metrics":{"Absolute relative error (AbsRel)":"0.089","RMSE":"5.481","RMSE log":"0.139","Square relative error (SqRel)":"1.051"},"uses_additional_data":false},{"leaderboard":"/sota/multi-task-learning-on-cityscapes","task":"Multi-Task Learning","dataset":"Cityscapes test","model":"SwinMTL","rank_in_archive_order":1,"of":3,"metrics":{"RMSE":"0.51","mIoU":"76.41"},"uses_additional_data":false},{"leaderboard":"/sota/multi-task-learning-on-nyuv2","task":"Multi-Task Learning","dataset":"NYUv2","model":"SwinMTL","rank_in_archive_order":1,"of":2,"metrics":{"Mean IoU":"58.14"},"uses_additional_data":false},{"leaderboard":"/sota/real-time-semantic-segmentation-on-cityscapes","task":"Real-Time Semantic Segmentation","dataset":"Cityscapes test","model":"SwinMTL","rank_in_archive_order":9,"of":39,"metrics":{"mIoU":"76.41%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-cityscapes","task":"Semantic Segmentation","dataset":"Cityscapes test","model":"SwinMTL","rank_in_archive_order":65,"of":105,"metrics":{"Mean IoU (class)":"76.41%"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-cityscapes-val","task":"Semantic Segmentation","dataset":"Cityscapes val","model":"SwinMTL","rank_in_archive_order":68,"of":99,"metrics":{"mIoU":"76.41"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-nyu-depth-v2","task":"Semantic Segmentation","dataset":"NYU Depth v2","model":"SwinMTL","rank_in_archive_order":11,"of":121,"metrics":{"Mean IoU":"58.14%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.10662","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}