Abstract
This paper studies the challenging problem of identifying unusual instances of known objects in images within an “open world” setting. That is, we aim to find objects thatare members of a known class, but which are not typical of that class. Thus the “unusual object” should be distinguished from both the “regular object” and the “other objects”. Such unusual objects may be of interest in manyapplications such as surveillance or quality control. We propose to identify unusual objects by inspecting the distribution of object detection scores at multiple image regions. The key observation motivating our approach isthat “regular object” images, “unusual object” images and“other objects” images exhibit different region-level scores in terms of both the score values and the spatial distributions. To model these distributions we propose to use Gaussian Processes (GP) to construct two separate generative models, one for the “regular object” and the other for the “other objects”. More specifically, we design a new covariance function to simultaneously model the detection score at a single location and the score dependencies between multiple regions. We demonstrate that the proposed approachoutperforms comparable methods on a new large datasetconstructed for the purpose.