通过扩展收缩操作提升二值神经网络表示能力，显著改善精度。
Expanding-and-Shrinking Binary Neural Networks
- 引入扩展-收缩操作增强二值特征图表达能力
- 在图像分类、目标检测等任务上超越主流二值化方法
- 适合作为高效模型部署时的精度优化方案
二值神经网络（BNNs）在速度、内存和能耗方面具有显著优势，但在复杂任务中相比实值网络存在严重精度下降。由于权重和激活的二值化，BNN生成的特征图取值范围受到强烈限制。为此，本文提出扩展-收缩操作，在计算开销几乎不变的前提下增强二值特征图的表示能力，从而提升模型表达力。在多个基准数据集上的大量实验表明，该方法在图像分类、目标检测及生成扩散模型等多种应用场景中均表现出良好泛化性，并在不同架构（包括CNN与Transformer）的多种先进二值化算法上取得显著性能提升。
原文摘要 · Abstract (English)
While binary neural networks (BNNs) offer significant benefits in terms of speed, memory and energy, they encounter substantial accuracy degradation in challenging tasks compared to their real-valued counterparts. Due to the binarization of weights and activations, the possible values of each entry in the feature maps generated by BNNs are strongly constrained. To tackle this limitation, we propose the expanding-and-shrinking operation, which enhances binary feature maps with negligible increase of computation complexity, thereby strengthening the representation capacity. Extensive experiments conducted on multiple benchmarks reveal that our approach generalizes well across diverse applications ranging from image classification, object detection to generative diffusion model, while also achieving remarkable improvement over various leading binarization algorithms based on different architectures including both CNNs and Transformers.
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。