{"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/hyt-nas-hybrid-transformers-neural","title":"HyT-NAS: Hybrid Transformers Neural Architecture Search for Edge Devices","arxiv_id":"2303.04440","date":"2023-03-08","proceeding":null,"authors":["Lotfi Abdelkrim Mecharbat","Hadjer Benmeziane","Hamza Ouarnoughi","Smail Niar"],"abstract":"Vision Transformers have enabled recent attention-based Deep Learning (DL) architectures to achieve remarkable results in Computer Vision (CV) tasks. However, due to the extensive computational resources required, these architectures are rarely implemented on resource-constrained platforms. Current research investigates hybrid handcrafted convolution-based and attention-based models for CV tasks such as image classification and object detection. In this paper, we propose HyT-NAS, an efficient Hardware-aware Neural Architecture Search (HW-NAS) including hybrid architectures targeting vision tasks on tiny devices. HyT-NAS improves state-of-the-art HW-NAS by enriching the search space and enhancing the search strategy as well as the performance predictors. Our experiments show that HyT-NAS achieves a similar hypervolume with less than ~5x training evaluations. Our resulting architecture outperforms MLPerf MobileNetV1 by 6.3% accuracy improvement with 3.5x less number of parameters on Visual Wake Words.","url_abs":"https://arxiv.org/abs/2303.04440v2","url_pdf":"https://arxiv.org/pdf/2303.04440v2.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":"hardware-aware-neural-architecture-search","task_name":"Hardware Aware Neural Architecture Search"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"architecture-search","task_name":"Neural Architecture Search"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"image-classification","task_name":"image-classification"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"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":"convolution","method_name":"Convolution"},{"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":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"mobilenetv1","method_name":"MobileNetV1"},{"method_slug":"pointwise-convolution","method_name":"Pointwise Convolution"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-visual-wake-words","task":"Image Classification","dataset":"Visual Wake Words","model":"HyT-NAS-BA","rank_in_archive_order":1,"of":4,"metrics":{"Accuracy":"92.25"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-visual-wake-words","task":"Image Classification","dataset":"Visual Wake Words","model":"ProxylessNAS","rank_in_archive_order":2,"of":4,"metrics":{"Accuracy":"86.55"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-visual-wake-words","task":"Image Classification","dataset":"Visual Wake Words","model":"MobileNetV2 (x0.35)","rank_in_archive_order":3,"of":4,"metrics":{"Accuracy":"86.34"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-visual-wake-words","task":"Image Classification","dataset":"Visual Wake Words","model":"MobileNetV1","rank_in_archive_order":4,"of":4,"metrics":{"Accuracy":"83.7"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}