How to train 4 bit mobilenent v2 to 72.0 (in the paper)?

[talenz]

Great job! In this paper, the top1 of 4bit mobilenetv2 is 72.0 and this is beyond SOTA. Is there a way that can reproduce this result?

[liujingcs]

Thanks for your interest. As mentioned in the supplementary material, we fine-tune the quantized model with additional learnable layer-wise offsets for activations and knowledge distillation following [1][2].
Reference:
[1] Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimation. CVPR 2022.
[2] PROFIT: A Novel Training Method for sub-4-bit MobileNet Models. ECCV 2020.

[talenz]

Will you provide the script to reproduce this result?