面向目标检测的任务特定零样本量化感知训练

摘要

量化是一种通过以较低精度表示网络参数来减小网络规模及计算复杂度的关键技术。传统量化方法依赖于对原始训练数据的访问，而由于隐私保护或安全挑战，这些数据往往受限。零样本量化（ZSQ）通过使用从预训练模型生成的合成数据，解决了这一问题，无需真实训练数据。最近，ZSQ已扩展至目标检测领域。然而，现有方法采用未标注的任务无关合成图像，缺乏目标检测所需的特定信息，导致性能欠佳。本文提出了一种新颖的面向目标检测网络的任务特定ZSQ框架，该框架包含两个主要阶段。首先，我们引入了一种边界框与类别采样策略，从预训练网络中合成任务特定的校准集，无需任何先验知识即可重建目标位置、大小及类别分布。其次，我们将任务特定训练融入知识蒸馏过程，以恢复量化检测网络的性能。在MS-COCO和Pascal VOC数据集上进行的大量实验验证了本方法的高效性和领先性能。我们的代码已公开于：https://github.com/DFQ-Dojo/dfq-toolkit。

English

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 .

面向目标检测的任务特定零样本量化感知训练

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

摘要

Support