{"ID":2891912,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.16782","arxiv_id":"2507.16782","title":"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 .","short_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 (...","url_abs":"https://arxiv.org/abs/2507.16782","url_pdf":"https://arxiv.org/pdf/2507.16782v1","authors":"[\"Changhao Li\",\"Xinrui Chen\",\"Ji Wang\",\"Kang Zhao\",\"Jianfei Chen\"]","published":"2025-07-22T17:28:29Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false,"code_links":[{"ID":611933,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2891912,"paper_url":"https://arxiv.org/abs/2507.16782","paper_title":"Task-Specific Zero-shot Quantization-Aware Training for Object Detection","repo_url":"https://github.com/DFQ-Dojo/dfq-toolkit","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}