paper-with-me

Papers

Task-Specific Zero-shot Quantization-Aware Training for Object Detection

2025-07-22 · Changhao Li, Xinrui Chen, Ji Wang, Kang Zhao, Jianfei Chen arxiv

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 .

📄 PDF Abstract BibTeX arXiv:2507.16782

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge DistillationObject Detection

Similar Papers 제목 키워드 기반

Genie: Show Me the Data for Quantization

2022-12-09 · CVPR 2023 1 · Yongkweon Jeon, Chungman Lee, Ho-young Kim

Zero-shot quantization is a promising approach for developing lightweight deep neural networks when data is inaccessible owing to various reasons, including cost and issues related to privacy. By exploiting the learned p…

Data Free QuantizationQuantization

Zero-Shot Sharpness-Aware Quantization for Pre-trained Language Models

2023-10-20 · Miaoxi Zhu, Qihuang Zhong, Li Shen, Liang Ding 외

Quantization is a promising approach for reducing memory overhead and accelerating inference, especially in large pre-trained language model (PLM) scenarios. While having no access to original training data due to securi…

Language ModelingLanguage ModellingQuantization

Sharpness-Aware Data Generation for Zero-shot Quantization

2025-10-08 · Dung Hoang-Anh, Cuong Pham Trung Le, Jianfei Cai, Thanh-Toan Do arxiv

Zero-shot quantization aims to learn a quantized model from a pre-trained full-precision model with no access to original real training data. The common idea in zero-shot quantization approaches is to generate synthetic …

Synthetic Data Generation

Infrared Domain Adaptation with Zero-Shot Quantization

2024-08-25 · Burak Sevsay, Erdem Akagündüz

Quantization is one of the most popular techniques for reducing computation time and shrinking model size. However, ensuring the accuracy of quantized models typically involves calibration using training data, which may …

Domain Adaptationobject-detectionObject DetectionQuantization

Zero-Shot Quantization via Weight-Space Arithmetic

2026-04-03 · Daniele Solombrino, Antonio Andrea Gargiulo, Alessandro Zirilli, Luca Zhou 외 arxiv

We show that robustness to post-training quantization (PTQ) is a transferable direction in weight space. We call this direction the quantization vector: extracted from a donor task by simple weight-space arithmetic, it c…

Image Classification