3 accepted papers
To enable the deployment of Vision Transformers on resource-constrained mobile and edge devices, the development of efficient ViT models has attracted significant attention. Researchers achieved remarkable improvements in accuracy and speed by optimizing attention mechanisms and integrating lightwei…
There are many AI applications in high-income countries because their implementation depends on expensive GPU cards (~2000$) and reliable power supply (~200W). To deploy AI in resource-poor settings on cheaper (~20$) and low-power devices (
Orthogonality regularization has proven effective in improving the precision, convergence speed and the training stability of CNNs. Here, we propose a novel Orthogonal Dictionary Convolution Strategy (ODCS) on CNNs to improve orthogonality effect by optimizing the network architecture and changing t…