Gradient Knows Best: Mixed-Precision Quantization via Gradient-Guided Bit Allocation for Super-Resolution
A novel PTQ-based MPQ framework tailored for SR models is proposed that outperforms existing PTQ-based methods by 1.26 dB in peak signal-to-noise ratio (PSNR) on the Urban100 dataset and introduces a dynamic activation range normalization that alleviates the distributional imbalance caused by the absence of BN.
Jun Young Kim, Joo Hyeon Jeon, Sangyeon Ahn et al.
· 0 citations