Task-Specific Zero-shot Quantization-Aware Training for Object Detection
Abstract
Quantization is a key technique to reduce network size and computational complexity by representing the network parameters with a lower precision. Traditional quantization methods rely on access to original training data, which is often restricted due to privacy concerns or security challenges. Zero-shot Quantization (ZSQ) addresses this by using synthetic data generated from pre-trained models, eliminating the need for real training data. Recently, ZSQ has been extended to object detection. However, existing methods use unlabeled task-agnostic synthetic images that lack the specific information required for object detection, leading to suboptimal performance. In this paper, we propose a novel task-specific ZSQ framework for object detection networks, which consists of two main stages. First, we introduce a bounding box and category sampling strategy to synthesize a task-specific calibration set from the pre-trained network, reconstructing object locations, sizes, and category distributions without any prior knowledge. Second, we integrate task-specific training into the knowledge distillation process to restore the performance of quantized detection networks. Extensive experiments conducted on the MS-COCO and Pascal VOC datasets demonstrate the efficiency and state-of-the-art performance of our method. Our code is publicly available at: https://github.com/DFQ-Dojo/dfq-toolkit .
Community
๐ Unlock Zero-Shot QAT Like Never Before!
We present a powerful plug-and-play Zero-Shot QAT framework that seamlessly supports four leading object detection backbones โ YOLOv5, YOLO11, Mask R-CNN, and ViT. Whether you're a researcher pushing the boundaries or a practitioner building real-world applications, this toolkit is your launchpad to rapid, calibration-free quantization!
๐ Code: https://github.com/DFQ-Dojo/dfq-toolkit
๐ Project Page: https://dfq-dojo.github.io/dfq-toolkit-webpage
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper