改进EfficientNetV2，提升垃圾分类准确率与实时性
An improved EfficientNetV2 for garbage classification
- 引入通道高效注意力模块，增强关键特征提取
- 在华为云数据集上达95.4%准确率，比基线高3.2%
- 适合实际场景中的高效垃圾分类系统
本文提出一种基于EfficientNetV2的改进垃圾分类框架，解决数据获取成本高、泛化能力弱和实时性差的问题。提出通道高效注意力（CE-Attention）模块，在不增加维度的情况下缓解全局池化导致的特征丢失，有效增强关键特征提取；同时设计轻量级多尺度空间特征提取模块（SAFM），通过深度可分离卷积显著降低模型复杂度。结合全面的数据增强策略提升泛化能力。在华为云垃圾分类数据集上的实验表明，该方法分类准确率达95.4%，较基线提升3.2%，优于主流模型。结果验证了该方法在准确率与效率间良好平衡，适用于实际垃圾分拣场景。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。