论文标题
在有雾天气下自动驾驶的域自适应对象检测
Domain Adaptive Object Detection for Autonomous Driving under Foggy Weather
论文作者
论文摘要
大多数用于自动驾驶的对象检测方法通常会在训练和测试数据之间具有一致的特征分布，而当天气差异很大时，这种情况并非总是如此。由于域间隙，在晴朗天气下训练的对象检测模型在雾气中可能不够有效。本文提出了一个新型的域自适应对象检测框架，用于在有雾天气下自动驾驶。我们的方法利用图像级和对象级的适应来减少图像样式和对象外观的域差异。为了进一步增强模型在有挑战性的样本下的功能，我们还提出了一个新的对抗性梯度逆转层，以对对抗性挖掘进行对抗性挖掘，并与域的适应性一起进行硬性示例。此外，我们建议通过数据增强生成辅助域，以实施新的域级公制正则化。公共基准的实验结果显示了所提出方法的有效性和准确性。该代码可在https://github.com/jinlong17/da-detect上找到。
Most object detection methods for autonomous driving usually assume a consistent feature distribution between training and testing data, which is not always the case when weathers differ significantly. The object detection model trained under clear weather might not be effective enough in foggy weather because of the domain gap. This paper proposes a novel domain adaptive object detection framework for autonomous driving under foggy weather. Our method leverages both image-level and object-level adaptation to diminish the domain discrepancy in image style and object appearance. To further enhance the model's capabilities under challenging samples, we also come up with a new adversarial gradient reversal layer to perform adversarial mining for the hard examples together with domain adaptation. Moreover, we propose to generate an auxiliary domain by data augmentation to enforce a new domain-level metric regularization. Experimental results on public benchmarks show the effectiveness and accuracy of the proposed method. The code is available at https://github.com/jinlong17/DA-Detect.
