Deploying high-performing neural networks in resource-constrained environments poses a significant challenge due to the computational demands of large-scale models. We introduce VL2Lite, a knowledge distillation framework designed to enhance the performance of lightweight neural networks in image classification tasks by leveraging the rich representational knowledge from Vision-Language Models (VLMs). VL2Lite directly integrates multi-modal knowledge from VLMs into compact models during training, effectively compensating for the limited computational and modeling capabilities of smaller networks. By transferring high-level features and complex data representations, our approach improves the accuracy and efficiency of image classification tasks without increasing computational overhead during inference. Experimental evaluations demonstrate that VL2Lite achieves up to a 7% improvement in classification performance across various datasets. This method addresses the challenge of deploying accurate models in environments with constrained computational resources, offering a balanced solution between model complexity and operational efficiency.

In this study, we propose a three-dimensional Medical image classifier using Multi-plane and Multi-slice Trans-former (M3T) network to classify Alzheimer's disease (AD) in 3D MRI images. The proposed network synergically com-bines 3D CNN, 2D CNN, and Transformer for accurate AD classification. The 3D CNN is used to perform natively 3D representation learning, while 2D CNN is used to utilize the pre-trained weights on large 2D databases and 2D repre-sentation learning. It is possible to efficiently extract the lo-cality information for AD-related abnormalities in the local brain using CNN networks with inductive bias. The trans-former network is also used to obtain attention relationships among multi-plane (axial, coronal, and sagittal) and multi-slice images after CNN. It is also possible to learn the ab-normalities distributed over the wider region in the brain using the transformer without inductive bias. In this ex-periment, we used a training dataset from the Alzheimer's Disease Neuroimaging Initiative (ADNI) which contains a total of 4,786 3D T1-weighted MRI images. For the validation data, we used dataset from three different institutions: The Australian Imaging, Biomarker and Lifestyle Flagship Study of Ageing (AIBL), The Open Access Series of Imaging Studies (OASIS), and some set of ADNI data indepen-dent from the training dataset. Our proposed M3T is compared to conventional 3D classification networks based on an area under the curve (AUC) and classification accuracy for AD classification. This study represents that the pro-posed network M3T achieved the highest performance in multi-institutional validation database, and demonstrates the feasibility of the method to efficiently combine CNN and Transformer for 3D medical images.