基于归一化流的特征合成用于异常值感知的目标检测
Normalizing Flow based Feature Synthesis for Outlier-Aware Object Detection
AI总结：
本文提出基于可逆归一化流学习所有内点类别联合分布以合成低似然异常值特征的异常值感知目标检测框架，在图像和视频数据集上显著超越现有方法。
摘要：
可靠目标检测器在自动驾驶等应用中的实际部署至关重要。然而，像Faster R-CNN这样的通用目标检测器容易对异常值目标给出过度自信的预测。最近的异常值感知目标检测方法使用类别条件高斯分布来估计实例级特征的密度，并从其低似然区域合成异常值特征进行训练。然而，这一策略并不能保证合成的异常值特征在其他类别条件高斯分布下也具有低似然。我们提出了一种新颖的异常值感知目标检测框架，通过使用可逆归一化流学习所有内点类别的联合数据分布，从而将异常值与内点目标区分开来。对归一化流模型的适当采样确保合成的异常值具有比所有目标类别的内点更低的似然，从而在内点和异常值目标之间建模出更好的决策边界。我们的方法在图像和视频数据集上的异常值感知目标检测中显著优于现有最先进方法。代码可在 https://github.com/nish03/FFS 获取。
英文摘要：
Real-world deployment of reliable object detectors is crucial for applications such as autonomous driving. However, general-purpose object detectors like Faster R-CNN are prone to providing overconfident predictions for outlier objects. Recent outlier-aware object detection approaches estimate the density of instance-wide features with class-conditional Gaussians and train on synthesized outlier features from their low-likelihood regions. However, this strategy does not guarantee that the synthesized outlier features will have a low likelihood according to the other class-conditional Gaussians. We propose a novel outlier-aware object detection framework that distinguishes outliers from inlier objects by learning the joint data distribution of all inlier classes with an invertible normalizing flow. The appropriate sampling of the flow model ensures that the synthesized outliers have a lower likelihood than inliers of all object classes, thereby modeling a better decision boundary between inlier and outlier objects. Our approach significantly outperforms the state-of-the-art for outlier-aware object detection on both image and video datasets. Code available at https://github.com/nish03/FFS
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。
