IntraQ: Learning Synthetic Images with Intra-Class Heterogeneity for Zero-Shot Network Quantization

11/17/2021
by   Yunshan Zhong, et al.
0

Learning to synthesize data has emerged as a promising direction in zero-shot quantization (ZSQ), which represents neural networks by low-bit integer without accessing any of the real data. In this paper, we observe an interesting phenomenon of intra-class heterogeneity in real data and show that existing methods fail to retain this property in their synthetic images, which causes a limited performance increase. To address this issue, we propose a novel zero-shot quantization method referred to as IntraQ. First, we propose a local object reinforcement that locates the target objects at different scales and positions of the synthetic images. Second, we introduce a marginal distance constraint to form class-related features distributed in a coarse area. Lastly, we devise a soft inception loss which injects a soft prior label to prevent the synthetic images from being overfitting to a fixed object. Our IntraQ is demonstrated to well retain the intra-class heterogeneity in the synthetic images and also observed to perform state-of-the-art. For example, compared to the advanced ZSQ, our IntraQ obtains 9.17% increase of the top-1 accuracy on ImageNet when all layers of MobileNetV1 are quantized to 4-bit. Code is at https://github.com/viperit/InterQ.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/13/2022

Long-Range Zero-Shot Generative Deep Network Quantization

Quantization approximates a deep network model with floating-point numbe...
research
03/24/2023

Hard Sample Matters a Lot in Zero-Shot Quantization

Zero-shot quantization (ZSQ) is promising for compressing and accelerati...
research
12/09/2022

Genie: Show Me the Data for Quantization

Zero-shot quantization is a promising approach for developing lightweigh...
research
03/31/2022

It's All In the Teacher: Zero-Shot Quantization Brought Closer to the Teacher

Model quantization is considered as a promising method to greatly reduce...
research
09/09/2021

Fine-grained Data Distribution Alignment for Post-Training Quantization

While post-training quantization receives popularity mostly due to its e...
research
12/19/2022

The case for 4-bit precision: k-bit Inference Scaling Laws

Quantization methods reduce the number of bits required to represent eac...
research
11/17/2022

Zero-Shot Dynamic Quantization for Transformer Inference

We introduce a novel run-time method for significantly reducing the accu...

Please sign up or login with your details

Forgot password? Click here to reset