{"ID":5438789,"CreatedAt":"2026-07-01T01:17:58.482524686Z","UpdatedAt":"2026-07-03T10:18:46.416236719Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.31456","arxiv_id":"2606.31456","title":"Zero-Shot Quantization for Object Detectors using Off-the-Shelf Generative Models","abstract":"With an increasing number of Object Detection (OD) models being deployed on edge devices, Zero-Shot Quantization for OD (ZSQ-OD) aims to quantize these models when access to the original training data is prohibited. Existing research on Zero-Shot Quantization-Aware Training (QAT) for OD synthesizes training sets through noise optimization. However, this approach struggles to maintain performance in low-bit regions. In this paper, we introduce GoodQ (Generative off-the-shelf models for object detector Quantization), a QAT pipeline that utilizes off-the-shelf generative models to construct a training set. We first identify three challenges that arise when introducing a generative model to the ZSQ-OD task: 1) each image contains dense information with multiple instances, 2) the class-wise distribution in the original dataset is imbalanced, and 3) the pseudo-labels assigned to the generated images can potentially act as noisy signals during QAT. GoodQ addresses these challenges by 1) introducing an Information-Dense Prompting strategy to generate multi-instance images, 2) applying Intrinsic Distribution-Aware Selection to match the pretrained class distribution, and 3) employing Teacher-guided Adaptive Noise Reduction to mitigate noise arising from the QAT process. Our framework achieves state-of-the-art performance in low-bit ZSQ (W4A4) and extends quantization to extreme bit-widths (W3A3). Furthermore, we conduct an extensive analysis to uncover the underlying factors contributing to the efficacy of GoodQ.","short_abstract":"With an increasing number of Object Detection (OD) models being deployed on edge devices, Zero-Shot Quantization for OD (ZSQ-OD) aims to quantize these models when access to the original training data is prohibited. Existing research on Zero-Shot Quantization-Aware Training (QAT) for OD synthesizes training sets throug...","url_abs":"https://arxiv.org/abs/2606.31456","url_pdf":"https://arxiv.org/pdf/2606.31456v1","authors":"[\"Hyunho Lee\",\"Kyomin Hwang\",\"Hyeonjin Kim\",\"Suyoung Kim\",\"Sunghyun Wee\",\"Nojun Kwak\"]","published":"2026-06-30T10:29:15Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[]","has_code":false}