@article{Li_Ding_Liu_Zhang_Guo_2021, title={TRQ: Ternary Neural Networks With Residual Quantization}, volume={35}, url={https://ojs.aaai.org/index.php/AAAI/article/view/17036}, DOI={10.1609/aaai.v35i10.17036}, abstractNote={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 stem-residual framework which provides new insight into Ternary quantization, termed 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. 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.}, number={10}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Li, Yue and Ding, Wenrui and Liu, Chunlei and Zhang, Baochang and Guo, Guodong}, year={2021}, month={May}, pages={8538-8546} }