{"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/gswin-gated-mlp-vision-model-with","title":"gSwin: Gated MLP Vision Model with Hierarchical Structure of Shifted Window","arxiv_id":"2208.11718","date":"2022-08-24","proceeding":null,"authors":["Mocho Go","Hideyuki Tachibana"],"abstract":"Following the success in language domain, the self-attention mechanism (transformer) is adopted in the vision domain and achieving great success recently. Additionally, as another stream, multi-layer perceptron (MLP) is also explored in the vision domain. These architectures, other than traditional CNNs, have been attracting attention recently, and many methods have been proposed. As one that combines parameter efficiency and performance with locality and hierarchy in image recognition, we propose gSwin, which merges the two streams; Swin Transformer and (multi-head) gMLP. We showed that our gSwin can achieve better accuracy on three vision tasks, image classification, object detection and semantic segmentation, than Swin Transformer, with smaller model size.","url_abs":"https://arxiv.org/abs/2208.11718v1","url_pdf":"https://arxiv.org/pdf/2208.11718v1.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":[],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"image-classification","task_name":"image-classification"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"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":"spatial-gating-unit","method_name":"Spatial Gating Unit"},{"method_slug":"stochastic-depth","method_name":"Stochastic Depth"},{"method_slug":"swin-transformer","method_name":"Swin Transformer"},{"method_slug":"transformer","method_name":"Transformer"},{"method_slug":"gmlp","method_name":"gMLP"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"gSwin-S","rank_in_archive_order":472,"of":1060,"metrics":{"GFLOPs":"7.0","Number of params":"39.8M","Top 1 Accuracy":"83.01%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"gSwin-T","rank_in_archive_order":613,"of":1060,"metrics":{"GFLOPs":"3.6","Number of params":"21.8M","Top 1 Accuracy":"81.71%"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-imagenet","task":"Image Classification","dataset":"ImageNet","model":"gSwin-VT","rank_in_archive_order":706,"of":1060,"metrics":{"GFLOPs":"2.3","Number of params":"15.5M","Top 1 Accuracy":"80.32%"},"uses_additional_data":false},{"leaderboard":"/sota/instance-segmentation-on-coco","task":"Instance Segmentation","dataset":"COCO test-dev","model":"gSwin-S","rank_in_archive_order":44,"of":112,"metrics":{"mask AP":"45.03"},"uses_additional_data":false},{"leaderboard":"/sota/instance-segmentation-on-coco","task":"Instance Segmentation","dataset":"COCO test-dev","model":"gSwin-T","rank_in_archive_order":46,"of":112,"metrics":{"mask AP":"44.16"},"uses_additional_data":false},{"leaderboard":"/sota/instance-segmentation-on-coco","task":"Instance Segmentation","dataset":"COCO test-dev","model":"gSwin-VT","rank_in_archive_order":52,"of":112,"metrics":{"mask AP":"42.87"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-ade20k-val","task":"Semantic Segmentation","dataset":"ADE20K val","model":"gSwin-S","rank_in_archive_order":55,"of":95,"metrics":{"Pixel Accuracy":"83.43","mIoU":"49.69"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-ade20k-val","task":"Semantic Segmentation","dataset":"ADE20K val","model":"gSwin-T","rank_in_archive_order":64,"of":95,"metrics":{"Pixel Accuracy":"82.60","mIoU":"47.63"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-ade20k-val","task":"Semantic Segmentation","dataset":"ADE20K val","model":"gSwin-VT","rank_in_archive_order":83,"of":95,"metrics":{"Pixel Accuracy":"81.79","mIoU":"45.07"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}