A Comparison for Patch-level Classification of Deep Learning Methods on Transparent Images: from Convolutional Neural Networks to Visual Transformers

Nowadays, analysis of transparent images in the field of computer vision has gradually become a hot spot. In this paper, we compare the classification performance of different deep learning for the problem that transparent images are difficult to analyze. We crop the transparent images into 8 * 8 and 224 * 224 pixels patches in the same proportion, and then divide the two different pixels patches into foreground and background according to groundtruch. We also use 4 types of convolutional neural networks and a novel ViT network model to compare the foreground and background classification experiments. We conclude that ViT performs the worst in classifying 8 * 8 pixels patches, but it outperforms most convolutional neural networks in classifying 224 * 224.