Post-Training Quantization for Object Detection

04/19/2023
by   Lin Niu, et al.
0

Efficient inference for object detection networks is a major challenge on edge devices. Post-Training Quantization (PTQ), which transforms a full-precision model into low bit-width directly, is an effective and convenient approach to reduce model inference complexity. But it suffers severe accuracy drop when applied to complex tasks such as object detection. PTQ optimizes the quantization parameters by different metrics to minimize the perturbation of quantization. The p-norm distance of feature maps before and after quantization, Lp, is widely used as the metric to evaluate perturbation. For the specialty of object detection network, we observe that the parameter p in Lp metric will significantly influence its quantization performance. We indicate that using a fixed hyper-parameter p does not achieve optimal quantization performance. To mitigate this problem, we propose a framework, DetPTQ, to assign different p values for quantizing different layers using an Object Detection Output Loss (ODOL), which represents the task loss of object detection. DetPTQ employs the ODOL-based adaptive Lp metric to select the optimal quantization parameters. Experiments show that our DetPTQ outperforms the state-of-the-art PTQ methods by a significant margin on both 2D and 3D object detectors. For example, we achieve 31.1/31.7(quantization/full-precision) mAP on RetinaNet-ResNet18 with 4-bit weight and 4-bit activation.

READ FULL TEXT
research
03/18/2021

Data-free mixed-precision quantization using novel sensitivity metric

Post-training quantization is a representative technique for compressing...
research
12/14/2022

PD-Quant: Post-Training Quantization based on Prediction Difference Metric

As a neural network compression technique, post-training quantization (P...
research
05/21/2018

DEEPEYE: A Compact and Accurate Video Comprehension at Terminal Devices Compressed with Quantization and Tensorization

As it requires a huge number of parameters when exposed to high dimensio...
research
07/14/2020

AQD: Towards Accurate Quantized Object Detection

Network quantization aims to lower the bitwidth of weights and activatio...
research
02/09/2022

Lightweight Jet Reconstruction and Identification as an Object Detection Task

We apply object detection techniques based on deep convolutional blocks ...
research
07/18/2021

A High-Performance Adaptive Quantization Approach for Edge CNN Applications

Recent convolutional neural network (CNN) development continues to advan...
research
07/28/2021

On Optimal Quantization in Sequential Detection

The problem of designing optimal quantization rules for sequential detec...

Please sign up or login with your details

Forgot password? Click here to reset