Cross Branch Feature Fusion Decoder for Consistency Regularization-based Semi-Supervised Change Detection
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909322974330880 |
|---|---|
| author | Xing, Yan Xu, Qi'ao Zeng, Jingcheng Huang, Rui Gao, Sihua Xu, Weifeng Zhang, Yuxiang Fan, Wei |
| author_facet | Xing, Yan Xu, Qi'ao Zeng, Jingcheng Huang, Rui Gao, Sihua Xu, Weifeng Zhang, Yuxiang Fan, Wei |
| contents | Semi-supervised change detection (SSCD) utilizes partially labeled data and a large amount of unlabeled data to detect changes. However, the transformer-based SSCD network does not perform as well as the convolution-based SSCD network due to the lack of labeled data. To overcome this limitation, we introduce a new decoder called Cross Branch Feature Fusion CBFF, which combines the strengths of both local convolutional branch and global transformer branch. The convolutional branch is easy to learn and can produce high-quality features with a small amount of labeled data. The transformer branch, on the other hand, can extract global context features but is hard to learn without a lot of labeled data. Using CBFF, we build our SSCD model based on a strong-to-weak consistency strategy. Through comprehensive experiments on WHU-CD and LEVIR-CD datasets, we have demonstrated the superiority of our method over seven state-of-the-art SSCD methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_15021 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Cross Branch Feature Fusion Decoder for Consistency Regularization-based Semi-Supervised Change Detection Xing, Yan Xu, Qi'ao Zeng, Jingcheng Huang, Rui Gao, Sihua Xu, Weifeng Zhang, Yuxiang Fan, Wei Computer Vision and Pattern Recognition Semi-supervised change detection (SSCD) utilizes partially labeled data and a large amount of unlabeled data to detect changes. However, the transformer-based SSCD network does not perform as well as the convolution-based SSCD network due to the lack of labeled data. To overcome this limitation, we introduce a new decoder called Cross Branch Feature Fusion CBFF, which combines the strengths of both local convolutional branch and global transformer branch. The convolutional branch is easy to learn and can produce high-quality features with a small amount of labeled data. The transformer branch, on the other hand, can extract global context features but is hard to learn without a lot of labeled data. Using CBFF, we build our SSCD model based on a strong-to-weak consistency strategy. Through comprehensive experiments on WHU-CD and LEVIR-CD datasets, we have demonstrated the superiority of our method over seven state-of-the-art SSCD methods. |
| title | Cross Branch Feature Fusion Decoder for Consistency Regularization-based Semi-Supervised Change Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.15021 |