Abstract
As global attention to environmental protection and sustainable resource utilization continues to rise, waste classification has emerged as a crucial issue that urgently needs to be addressed in the context of social development. Proper waste sorting not only helps reduce environmental pollution but also significantly enhances resource recycling rates, playing a vital role in promoting green and sustainable development. Compared to traditional manual waste sorting methods, deep learning-based waste classification systems offer remarkable advantages. This paper proposes an innovative deep learning framework named Garbage FusionNet (GFN) to tackle the waste classification problem. GFN significantly improves the classification performance by combining the local feature extraction capabilities of ResNet with the global information capturing abilities of Vision Transformer (ViT). GFN outperforms existing benchmark models on a ten-category waste classification dataset comprising 23,642 images. Experimental results demonstrate that GFN achieves superior performance on key metrics such as accuracy, weighted precision, weighted recall, and weighted F1-score. Specifically, GFN achieves an accuracy of 96.54%, surpassing standalone ResNet50 and ViT models by 1.09 and 4.18 percentage points, respectively. GFN offers an efficient and reliable solution for waste classification, highlighting the potential of deep learning in environmental protection.