An improved EfficientNetV2 for garbage classification
This addresses waste classification for practical applications, but it's incremental as it builds on existing EfficientNetV2 with specific modifications.
This paper tackles garbage classification by enhancing EfficientNetV2 with a Channel-Efficient Attention module and lightweight multi-scale feature extraction, achieving 95.4% accuracy on a Huawei Cloud dataset, which is 3.2% higher than the baseline.
This paper presents an enhanced waste classification framework based on EfficientNetV2 to address challenges in data acquisition cost, generalization, and real-time performance. We propose a Channel-Efficient Attention (CE-Attention) module that mitigates feature loss during global pooling without introducing dimensional scaling, effectively enhancing critical feature extraction. Additionally, a lightweight multi-scale spatial feature extraction module (SAFM) is developed by integrating depthwise separable convolutions, significantly reducing model complexity. Comprehensive data augmentation strategies are further employed to improve generalization. Experiments on the Huawei Cloud waste classification dataset demonstrate that our method achieves a classification accuracy of 95.4\%, surpassing the baseline by 3.2\% and outperforming mainstream models. The results validate the effectiveness of our approach in balancing accuracy and efficiency for practical waste classification scenarios.