Model binarization is an effective method of compressing neural networks and accelerating their inference process. However, a significant performance gap still exists between the 1-bit model and the 32-bit one. The empirical study shows that binarization causes a great loss of information in the forward and backward propagation. We present a novel Distribution-sensitive Information Retention Network (DIR-Net) that retains the information in the forward and backward propagation by improving internal propagation and introducing external representations. The DIR-Net mainly relies on three technical contributions: (1) Information Maximized Binarization (IMB): minimizing the information loss and the binarization error of weights/activations simultaneously by weight balance and standardization; (2) Distribution-sensitive Two-stage Estimator (DTE): retaining the information of gradients by distribution-sensitive soft approximation by jointly considering the updating capability and accurate gradient; (3) Representation-align Binarization-aware Distillation (RBD): retaining the representation information by distilling the representations between full-precision and binarized networks. The DIR-Net investigates both forward and backward processes of BNNs from the unified information perspective, thereby providing new insight into the mechanism of network binarization. The three techniques in our DIR-Net are versatile and effective and can be applied in various structures to improve BNNs. Comprehensive experiments on the image classification and objective detection tasks show that our DIR-Net consistently outperforms the state-of-the-art binarization approaches under mainstream and compact architectures, such as ResNet, VGG, EfficientNet, DARTS, and MobileNet. Additionally, we conduct our DIR-Net on real-world resource-limited devices which achieves 11.1x storage saving and 5.4x speedup.
翻译:模型二进制是压缩神经网络并加速其循环过程的有效方法。然而,在1比特模型和32比特模型之间仍然存在着巨大的绩效差距。经验研究表明,二进制在前向和后向传播中造成了信息的巨大损失。我们提出了一个新的对分发敏感的信息保存网(DIR-Net),通过改进内部传播和引入外部演示,保留前向和后向传播的信息。 DIR-Net主要依靠三种技术贡献:(1) 信息最大化网络化(IMB):通过权重平衡和标准化,最大限度地减少信息损失和加权/内向网络激活的二进制错误;(2) 配制敏感的双阶段数据模拟(DTE):通过联合考虑更新能力和准确梯度,对分配敏感的信息保存梯度信息网络信息;(3) 代表-感知-感知-感知-更新(RBDDD):通过淡化全面精化和二进化网络的表达方式,DIR网络的前向前向和后升级进程,在BNS-RO-S 快速存储技术下,从而从我们连续地将数据转换到内部结构,从而显示我们的各种信息流流流化,从而显示我们的数据结构中,在各种结构中,可以显示我们采用。