论文标题
保险箱：敏感性感知到分布对象检测的功能
SAFE: Sensitivity-Aware Features for Out-of-Distribution Object Detection
论文作者
论文摘要
我们解决了对象检测任务的分布外（OOD）检测问题。我们表明，具有批准化的残留卷积层会产生灵敏度感知的特征（安全），这些特征始终强大，可将分布与分布式检测区分开。我们为每个检测到的对象提取安全矢量，并在替代任务上训练多层感知器，以区分对抗性的对抗性扰动与干净的分布示例。这规定了对现实的OOD培训数据，计算昂贵的生成模型或基本对象检测器的重新训练的需求。安全的表现优于多个基准的最新OOD对象检测器，例如在OpenImages数据集中，将FPR95从48.3％降低至17.7％。
We address the problem of out-of-distribution (OOD) detection for the task of object detection. We show that residual convolutional layers with batch normalisation produce Sensitivity-Aware FEatures (SAFE) that are consistently powerful for distinguishing in-distribution from out-of-distribution detections. We extract SAFE vectors for every detected object, and train a multilayer perceptron on the surrogate task of distinguishing adversarially perturbed from clean in-distribution examples. This circumvents the need for realistic OOD training data, computationally expensive generative models, or retraining of the base object detector. SAFE outperforms the state-of-the-art OOD object detectors on multiple benchmarks by large margins, e.g. reducing the FPR95 by an absolute 30.6% from 48.3% to 17.7% on the OpenImages dataset.
