让二值化网络更准更快，实现高效密集预测
BiDense: Binarization for Dense Prediction
- 用自适应阈值和通道级精度旁路提升二值网络性能
- 在多个数据集上达到接近全精度模型的准确率
- 适合部署在资源受限设备上的图像分割等任务
密集预测是计算机视觉中的关键任务，但以往方法常需大量计算资源，限制了实际应用。本文提出BiDense，一种面向高效且精确密集预测的通用二值神经网络。该方法引入两项关键技术：分布自适应二值化器（DAB）和通道自适应全精度旁路（CFB）。DAB 自适应计算二值化阈值与缩放因子，有效保留BNN中的信息；CFB 为经历不同通道数变换的二值卷积层提供全精度信号通路，增强真实值信号传播并减少信息损失。结合两项技术，BiDense 能更好保留实值信息，实现更精准、细致的密集预测。大量实验表明，该框架性能可媲美全精度模型，同时显著降低内存占用与计算开销。
原文摘要 · Abstract (English)
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.
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。