提出1.58位卷积与预归一化残差连接，首次实现深度可分离卷积的二值化。
BD-Net: Has Depth-Wise Convolution Ever Been Applied in Binary Neural Networks?
- 用1.58位卷积提升表达能力，结合预归一化残差稳定训练过程。
- 在ImageNet上仅3300万次操作即达新SOTA，比现有方法高9.3个百分点。
- 适用于移动端轻量模型，尤其适合对效率要求高的部署场景。
近年来，模型压缩技术的发展突显了低比特精度方法的潜力，二值神经网络（BNNs）因其极高的效率受到关注。然而，极端量化导致表达能力受限且训练不稳定，给具有深度可分离卷积的轻量级架构带来挑战。为此，我们提出一种1.58位卷积以增强表达性，并引入预归一化残差连接通过改善海森矩阵条件数来稳定优化。这些创新使我们首次成功实现了在BNN中对深度可分离卷积的二值化。该方法在ImageNet上仅需33M OPs即可达到新的最佳性能，显著优于此前方法。此外，它在多个数据集（包括CIFAR-10、CIFAR-100、STL-10、Tiny ImageNet和Oxford Flowers 102）上均表现更优，最高准确率提升达9.3个百分点。
原文摘要 · Abstract (English)
Recent advances in model compression have highlighted the potential of low-bit precision techniques, with Binary Neural Networks (BNNs) attracting attention for their extreme efficiency. However, extreme quantization in BNNs limits representational capacity and destabilizes training, posing significant challenges for lightweight architectures with depth-wise convolutions. To address this, we propose a 1.58-bit convolution to enhance expressiveness and a pre-BN residual connection to stabilize optimization by improving the Hessian condition number. These innovations enable, to the best of our knowledge, the first successful binarization of depth-wise convolutions in BNNs. Our method achieves 33M OPs on ImageNet with MobileNet V1, establishing a new state-of-the-art in BNNs by outperforming prior methods with comparable OPs. Moreover, it consistently outperforms existing methods across various datasets, including CIFAR-10, CIFAR-100, STL-10, Tiny ImageNet, and Oxford Flowers 102, with accuracy improvements of up to 9.3 percentage points.
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。