Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.21208 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917968984670208 |
|---|---|
| author | Qiu, Wenxuan Xie, Chengxin Huang, Jingui |
| author_facet | Qiu, Wenxuan Xie, Chengxin Huang, Jingui |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_21208 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | An improved EfficientNetV2 for garbage classification Qiu, Wenxuan Xie, Chengxin Huang, Jingui Computer Vision and Pattern Recognition 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. |
| title | An improved EfficientNetV2 for garbage classification |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.21208 |