面向物體檢測的任務特定零樣本量化感知訓練

摘要

量化是一種關鍵技術，通過以較低精度表示網絡參數來減少網絡規模和計算複雜度。傳統的量化方法依賴於對原始訓練數據的訪問，但由於隱私問題或安全挑戰，這些數據往往受到限制。零樣本量化（ZSQ）通過使用從預訓練模型生成的合成數據來解決這一問題，從而消除了對真實訓練數據的需求。最近，ZSQ已被擴展到目標檢測領域。然而，現有方法使用未標記的任務無關合成圖像，這些圖像缺乏目標檢測所需的特定信息，導致性能不佳。在本文中，我們提出了一種新穎的任務特定ZSQ框架，用於目標檢測網絡，該框架包含兩個主要階段。首先，我們引入了一種邊界框和類別採樣策略，從預訓練網絡中合成任務特定的校準集，在沒有任何先驗知識的情況下重建物體位置、大小和類別分佈。其次，我們將任務特定訓練整合到知識蒸餾過程中，以恢復量化檢測網絡的性能。在MS-COCO和Pascal VOC數據集上進行的大量實驗證明了我們方法的效率和最先進的性能。我們的代碼公開在：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 .

面向物體檢測的任務特定零樣本量化感知訓練

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

摘要

Support