研究量化后目标检测模型在噪声模糊等退化下的鲁棒性，提出新校准方法但效果有限。
Quantization Robustness to Input Degradations for Object Detection
- 用混合清晰与退化图像进行校准，提升量化模型对输入退化的适应能力。
- 静态INT8量化使推理速度提升1.5-3.3倍，但清画面下准确率下降3-7% mAP50-95。
- 大模型在特定噪声下表现更好，说明模型规模影响校准有效性，适合边缘部署研究者参考。
后训练量化（PTQ）对在资源受限设备上部署高效目标检测模型（如YOLO）至关重要。然而，精度降低对模型在真实世界输入退化（如噪声、模糊、压缩伪影）下鲁棒性的影响是一个关键问题。本文对YOLO系列模型（从nano到extra-large）在多种精度格式（FP32、FP16、动态UINT8、静态INT8）下的鲁棒性进行了全面实证研究。提出一种退化感知的静态INT8 PTQ校准策略，即在TensorRT校准过程中引入混合的干净与合成退化图像。模型在COCO数据集上于七种不同退化条件（包括多种噪声、模糊、低对比度和JPEG压缩）及混合退化场景下进行评测。结果表明，虽然静态INT8 TensorRT引擎在干净数据上实现约1.5-3.3倍的速度提升，且准确率仅下降3-7% mAP50-95，但该退化感知校准在多数模型和退化条件下并未带来一致且广泛的鲁棒性提升。仅在大模型规模下特定噪声条件下观察到显著改善，暗示模型容量可能影响校准方法的有效性。这些发现揭示了提升量化鲁棒性的挑战，并为在非控制环境下部署量化检测器提供了洞见。所有代码与评估表格详见https://github.com/AllanK24/QRID。
原文摘要 · Abstract (English)
Post-training quantization (PTQ) is crucial for deploying efficient object detection models, like YOLO, on resource-constrained devices. However, the impact of reduced precision on model robustness to real-world input degradations such as noise, blur, and compression artifacts is a significant concern. This paper presents a comprehensive empirical study evaluating the robustness of YOLO models (nano to extra-large scales) across multiple precision formats: FP32, FP16 (TensorRT), Dynamic UINT8 (ONNX), and Static INT8 (TensorRT). We introduce and evaluate a degradation-aware calibration strategy for Static INT8 PTQ, where the TensorRT calibration process is exposed to a mix of clean and synthetically degraded images. Models were benchmarked on the COCO dataset under seven distinct degradation conditions (including various types and levels of noise, blur, low contrast, and JPEG compression) and a mixed-degradation scenario. Results indicate that while Static INT8 TensorRT engines offer substantial speedups (~1.5-3.3x) with a moderate accuracy drop (~3-7% mAP50-95) on clean data, the proposed degradation-aware calibration did not yield consistent, broad improvements in robustness over standard clean-data calibration across most models and degradations. A notable exception was observed for larger model scales under specific noise conditions, suggesting model capacity may influence the efficacy of this calibration approach. These findings highlight the challenges in enhancing PTQ robustness and provide insights for deploying quantized detectors in uncontrolled environments. All code and evaluation tables are available at https://github.com/AllanK24/QRID.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。