在雨天或晴天：理解和克服数据集偏差，以提高自动驾驶汽车对天气破坏的鲁棒性
In Rain or Shine: Understanding and Overcoming Dataset Bias for Improving Robustness Against Weather Corruptions for Autonomous Vehicles
摘要：
几种流行的计算机视觉（CV）数据集，特别是用于自动驾驶任务中的目标检测（OD）的数据集，由于包括天气和照明条件在内的一系列因素而表现出偏差。这些偏差可能会损害模型的泛化能力，使其在新的和看不见的数据集中对OD无效。特别是在自动驾驶中，它可能对车辆及其周围环境具有极高的风险和不安全性。这项工作的重点是通过识别这种“好天气”偏差来更好地理解这些数据集。还证明了减轻这种偏差的方法，从而使OD模型能够更好地执行并提高鲁棒性。提出了一个简单而有效的OD框架，用于研究偏差缓解。使用这个框架，流行的数据集上的性能进行了分析，并观察到模型性能的显着差异。此外，提出了一种知识转移技术和合成图像腐败技术，以减轻所识别的偏见。最后，使用DAWN数据集，在OD任务上验证了研究结果，证明了我们的技术在减轻现实世界中的“好天气”偏见方面的有效性。实验结果表明，所提出的技术优于基线方法的平均四倍的改善。
英文摘要：
Several popular computer vision (CV) datasets, specifically employed for Object Detection (OD) in autonomous driving tasks exhibit biases due to a range of factors including weather and lighting conditions. These biases may impair a model's generalizability, rendering it ineffective for OD in novel and unseen datasets. Especially, in autonomous driving, it may prove extremely high risk and unsafe for the vehicle and its surroundings. This work focuses on understanding these datasets better by identifying such "good-weather" bias. Methods to mitigate such bias which allows the OD models to perform better and improve the robustness are also demonstrated. A simple yet effective OD framework for studying bias mitigation is proposed. Using this framework, the performance on popular datasets is analyzed and a significant difference in model performance is observed. Additionally, a knowledge transfer technique and a synthetic image corruption technique are proposed to mitigate the identified bias. Finally, using the DAWN dataset, the findings are validated on the OD task, demonstrating the effectiveness of our techniques in mitigating real-world "good-weather" bias. The experiments show that the proposed techniques outperform baseline methods by averaged fourfold improvement.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
