Fine-grained Data Distribution Alignment for Post-Training Quantization

Understand

While post-training quantization receives popularity mostly due to its evasion in accessing the original complete training dataset, its poor performance also stems from scarce images.

• To alleviate this limitation, in this paper, we leverage the synthetic data introduced by zero-shot quantization with calibration dataset and propose a fine-grained data distribution alignment (FDDA) method to boost the performance of post-training quantization.
• The method is based on two important properties of batch normalization statistics (BNS) we observed in deep layers of the trained network, (i.e.), inter-class separation and intra-class incohesion.
• To preserve this fine-grained distribution information: 1) We calculate the per-class BNS of the calibration dataset as the BNS centers of each class and propose a BNS-centralized loss to force the synthetic data distributions of different classes to be close to their own centers.