Pixel Invisibility: Detecting Objects Invisible in Color Images
This addresses safety risks in autonomous systems by quantifying detection failures under operational conditions like night and fog, though it is an incremental improvement using cross-modal distillation.
The paper tackles the problem of unreliable object detection in safety-critical applications like self-driving cars under varying lighting conditions by developing an algorithm that predicts pixel-level invisibility maps for color images without manual labeling, showing great performance in quantitative experiments.
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.