论文标题
像素隐形：检测颜色图像中的对象看不见
Pixel Invisibility: Detecting Objects Invisible in Color Images
论文作者
论文摘要
尽管对象探测器使用深层神经网络最近成功，但它们在自动驾驶汽车等安全性关键应用上的部署仍然值得怀疑。这部分是由于在夜间，雾，黄昏，黎明和眩光等操作条件下检测器失败的可靠估计。这种不量化的失败可能导致违反安全性。为了解决此问题，我们创建了一种算法，该算法可预测不需要手动标签的颜色图像的像素级别的隐形图 - 计算像素/区域在各种照明条件（如白天，夜晚和雾中）中包含在颜色域中不可见的对象的概率。我们提出了一种新颖的使用，该新颖的使用是使用当天弱对齐的图像对从颜色到红外域的新颖使用，并基于其中间级特征的距离构造像素级别的隐形性。定量实验显示了我们像素级的隐形掩码的出色表现，以及蒸馏中级特征在红外图像中对象检测中的有效性。
Despite recent success of object detectors using deep neural networks, their deployment on safety-critical applications such as self-driving cars remains questionable. This is partly due to the absence of reliable estimation for detectors' failure under operational conditions such as night, fog, dusk, dawn and glare. Such unquantifiable failures could lead to safety violations. In order to solve this problem, we created an algorithm that predicts a pixel-level invisibility map for color images that does not require manual labeling - that computes the probability that a pixel/region contains objects that are invisible in color domain, during various lighting conditions such as day, night and fog. We propose a novel use of cross modal knowledge distillation from color to infra-red domain using weakly-aligned image pairs from the day and construct indicators for the pixel-level invisibility based on the distances of their intermediate-level features. Quantitative experiments show the great performance of our pixel-level invisibility mask and also the effectiveness of distilled mid-level features on object detection in infra-red imagery.
