Advanced Knowledge Transfer: Refined Feature Distillation for Zero-Shot Quantization in Edge Computing
This addresses a bottleneck in deploying efficient models on edge devices, though it appears incremental as it builds on existing generative models in zero-shot quantization.
The paper tackles the problem of reduced learning ability in low-bit quantized models for zero-shot quantization by proposing AKT, a method that refines feature maps during distillation to transfer knowledge more effectively, achieving state-of-the-art accuracy in 3-bit and 5-bit scenarios on CIFAR-10.
We introduce AKT (Advanced Knowledge Transfer), a novel method to enhance the training ability of low-bit quantized (Q) models in the field of zero-shot quantization (ZSQ). Existing research in ZSQ has focused on generating high-quality data from full-precision (FP) models. However, these approaches struggle with reduced learning ability in low-bit quantization due to its limited information capacity. To overcome this limitation, we propose effective training strategy compared to data generation. Particularly, we analyzed that refining feature maps in the feature distillation process is an effective way to transfer knowledge to the Q model. Based on this analysis, AKT efficiently transfer core information from the FP model to the Q model. AKT is the first approach to utilize both spatial and channel attention information in feature distillation in ZSQ. Our method addresses the fundamental gradient exploding problem in low-bit Q models. Experiments on CIFAR-10 and CIFAR-100 datasets demonstrated the effectiveness of the AKT. Our method led to significant performance enhancement in existing generative models. Notably, AKT achieved significant accuracy improvements in low-bit Q models, achieving state-of-the-art in the 3,5bit scenarios on CIFAR-10. The code is available at https://github.com/Inpyo-Hong/AKT-Advanced-knowledge-Transfer.