TRQ: Ternary Neural Networks With Residual Quantization

Ternary neural networks (TNNs) are potential for network acceleration by reducing the full-precision weights in network to ternary ones, e.g., -1, 0, 1. However, existing TNNs are mostly calculated based on rule-of-thumb quantization methods by simply thresholding operations, which causes a significant accuracy loss. In this paper, we introduce a stemresidual framework which provides new insight into ternary quantization, termed Ternary Residual Quantization (TRQ), to achieve more powerful TNNs. Rather than directly thresholding operations, TRQ recursively performs quantization on full-precision weights for a refined reconstruction by combining the binarized stem and residual parts.With such a unique quantization process, TRQ endows the quantizer with high flexibility and precision. Furthermore, our TRQ is generic, which can be easily extended to multiple bits through recursively encoded residual for a better recognition accuracy. Extensive experimental results demonstrate that the proposed method yields great recognition accuracy while being accelerated.