Navigating Efficiency in MobileViT through Gaussian Process on Global Architecture Factors
Numerous techniques have been meticulously designed to achieve optimal architectures for convolutional neural networks (CNNs), yet a comparable focus on vision transformers (ViTs) has been somewhat lacking. Despite the remarkable success of ViTs in various vision tasks, their heavyweight nature presents challenges of computational costs. In this paper, we leverage the Gaussian process to systematically explore the nonlinear and uncertain relationship between performance and global architecture factors of MobileViT, such as resolution, width, and depth including the depth of in-verted residual blocks and the depth of ViT blocks, and joint factors including resolution-depth and resolution-width. We present design principles twisting magic 4D cube of the global architecture factors that minimize model sizes and computational costs with higher model accuracy. We introduce a formula for downsizing architectures by iteratively deriving smaller MobileViT V2, all while adhering to a specified constraint of multiply-accumulate operations (MACs). Experiment results show that our formula significantly outperforms CNNs and mobile ViTs across diversified datasets
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
An Enhancement of CNN Algorithm for Rice Leaf Disease Image Classification in Mobile Applications
This study focuses on enhancing rice leaf disease image classification algorithms, which have traditionally relied on Convolutional Neural Network (CNN) models. We employed transfer learning with MobileViTV2_050 using Im…
Computational Efficiencyimage-classificationImage ClassificationTransfer LearningOnboard Satellite Image Classification for Earth Observation: A Comparative Study of ViT Models
This study focuses on identifying the most effective pre-trained model for land use classification in onboard satellite processing, emphasizing achieving high accuracy, computational efficiency, and robustness against no…
Computational EfficiencyEarth Observationimage-classificationImage Classification+2MobileViTv3: Mobile-Friendly Vision Transformer with Simple and Effective Fusion of Local, Global and Input Features
MobileViT (MobileViTv1) combines convolutional neural networks (CNNs) and vision transformers (ViTs) to create light-weight models for mobile vision tasks. Though the main MobileViTv1-block helps to achieve competitive s…
Image ClassificationObject DetectionSemantic SegmentationSeparable Self-attention for Mobile Vision Transformers
Mobile vision transformers (MobileViT) can achieve state-of-the-art performance across several mobile vision tasks, including classification and detection. Though these models have fewer parameters, they have high latenc…
Image ClassificationObject DetectionMobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer
Light-weight convolutional neural networks (CNNs) are the de-facto for mobile vision tasks. Their spatial inductive biases allow them to learn representations with fewer parameters across different vision tasks. However,…
Image Classificationobject-detectionObject Detection