BiDense: Binarization for Dense Prediction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yin, Rui, Qin, Haotong, Zhang, Yulun, Li, Wenbo, Guo, Yong, Zhu, Jianjun, Wang, Cheng, Jia, Biao
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