BiDense: Binarization for Dense Prediction
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_ | 1866917843296059392 |
|---|---|
| author | Yin, Rui Qin, Haotong Zhang, Yulun Li, Wenbo Guo, Yong Zhu, Jianjun Wang, Cheng Jia, Biao |
| author_facet | Yin, Rui Qin, Haotong Zhang, Yulun Li, Wenbo Guo, Yong Zhu, Jianjun Wang, Cheng Jia, Biao |
| contents | Dense prediction is a critical task in computer vision. However, previous methods often require extensive computational resources, which hinders their real-world application. In this paper, we propose BiDense, a generalized binary neural network (BNN) designed for efficient and accurate dense prediction tasks. BiDense incorporates two key techniques: the Distribution-adaptive Binarizer (DAB) and the Channel-adaptive Full-precision Bypass (CFB). The DAB adaptively calculates thresholds and scaling factors for binarization, effectively retaining more information within BNNs. Meanwhile, the CFB facilitates full-precision bypassing for binary convolutional layers undergoing various channel size transformations, which enhances the propagation of real-valued signals and minimizes information loss. By leveraging these techniques, BiDense preserves more real-valued information, enabling more accurate and detailed dense predictions in BNNs. Extensive experiments demonstrate that our framework achieves performance levels comparable to full-precision models while significantly reducing memory usage and computational costs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_10346 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | BiDense: Binarization for Dense Prediction Yin, Rui Qin, Haotong Zhang, Yulun Li, Wenbo Guo, Yong Zhu, Jianjun Wang, Cheng Jia, Biao Computer Vision and Pattern Recognition Dense prediction is a critical task in computer vision. However, previous methods often require extensive computational resources, which hinders their real-world application. In this paper, we propose BiDense, a generalized binary neural network (BNN) designed for efficient and accurate dense prediction tasks. BiDense incorporates two key techniques: the Distribution-adaptive Binarizer (DAB) and the Channel-adaptive Full-precision Bypass (CFB). The DAB adaptively calculates thresholds and scaling factors for binarization, effectively retaining more information within BNNs. Meanwhile, the CFB facilitates full-precision bypassing for binary convolutional layers undergoing various channel size transformations, which enhances the propagation of real-valued signals and minimizes information loss. By leveraging these techniques, BiDense preserves more real-valued information, enabling more accurate and detailed dense predictions in BNNs. Extensive experiments demonstrate that our framework achieves performance levels comparable to full-precision models while significantly reducing memory usage and computational costs. |
| title | BiDense: Binarization for Dense Prediction |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2411.10346 |