The Overlooked Elephant of Object Detection: Open Set

Akshay Dhamija, Manuel Gunther, Jonathan Ventura, Terrance Boult; Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2020, pp. 1021-1030

Abstract


Even though object detection is a popular area of research that has found considerable applications in the real world, it has some fundamental aspects that have never been formally discussed and experimented. One of the core aspects of evaluating object detectors has been the ability to avoid false detections. While major datasets like PASCAL VOC or MSCOCO extensively test the detectors on their ability to avoid false positives, they do not differentiate between their closed-set and open-set performance. Despite systems being trained to reject everything other than the classes of interest, unknown objects from the open world end up being incorrectly detected as known objects, often with very high confidence. This paper is the first to formalize the problem of open-set object detection and propose the first open-set object detection protocol. Moreover, the paper provides a new evaluation metric to analyze the performance of some state-of-the-art detectors and discusses their performance differences.

Related Material


[pdf] [supp] [video]
[bibtex]
@InProceedings{Dhamija_2020_WACV,
author = {Dhamija, Akshay and Gunther, Manuel and Ventura, Jonathan and Boult, Terrance},
title = {The Overlooked Elephant of Object Detection: Open Set},
booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
month = {March},
year = {2020}
}