Managing Household Waste through Transfer Learning
Suman Kunwar
TL;DR
The paper addresses waste classification using transfer learning while accounting for ecological cost. It benchmarks five TL architectures (EfficientNetV2S/M, MobileNet, ResNet50/101) on a 23,672-image, 10-class garbage dataset and measures accuracy, recall, F1, IoU, training time, and carbon emissions with codecarbon. The results show EfficientNetV2S as the most sustainable and accurate (96.41% after hyperparameter tuning), with EfficientNetV2M offering higher accuracy but at greater compute and emissions; ResNet50 provides competitive accuracy but higher carbon footprints, while MobileNet underperforms. The work contributes a framework for evaluating both predictive performance and environmental impact in ML-driven waste management, supporting sustainable deployment decisions.
Abstract
As the world continues to face the challenges of climate change, it is crucial to consider the environmental impact of the technologies we use. In this study, we investigate the performance and computational carbon emissions of various transfer learning models for garbage classification. We examine the MobileNet, ResNet50, ResNet101, and EfficientNetV2S and EfficientNetV2M models. Our findings indicate that the EfficientNetV2 family achieves the highest accuracy, recall, f1-score, and IoU values. However, the EfficientNetV2M model requires more time and produces higher carbon emissions. ResNet50 outperforms ResNet110 in terms of accuracy, recall, f1-score, and IoU, but it has a larger carbon footprint. We conclude that EfficientNetV2S is the most sustainable and accurate model with 96.41% accuracy. Our research highlights the significance of considering the ecological impact of machine learning models in garbage classification.