False Detection (Positives and Negatives) in Object Detection
This work addresses accuracy issues in object detection systems, but it appears incremental as it focuses on empirical experiments without introducing new methods.
The study tackled the problem of false positives and negatives in object detection by exploring methods to reduce them using labeled data, and discovered insufficient labeling in the Openimage 2019 dataset.
Object detection is a very important function of visual perception systems. Since the early days of classical object detection based on HOG to modern deep learning based detectors, object detection has improved in accuracy. Two stage detectors usually have higher accuracy than single stage ones. Both types of detectors use some form of quantization of the search space of rectangular regions of image. There are far more of the quantized elements than true objects. The way these bounding boxes are filtered out possibly results in the false positive and false negatives. This empirical experimental study explores ways of reducing false positives and negatives with labelled data.. In the process also discovered insufficient labelling in Openimage 2019 Object Detection dataset.