Dropout Sampling for Robust Object Detection in Open-Set Conditions
This addresses the challenge of improving object detection reliability for robotic vision in unpredictable environments, representing an incremental advancement by adapting an existing technique to a new task.
The paper tackled the problem of robust object detection in open-set conditions by applying Dropout Sampling to extract label uncertainty from a state-of-the-art object detection system, resulting in a 12.3% increase in recall and a 15.1% increase in precision compared to a standard network.
Dropout Variational Inference, or Dropout Sampling, has been recently proposed as an approximation technique for Bayesian Deep Learning and evaluated for image classification and regression tasks. This paper investigates the utility of Dropout Sampling for object detection for the first time. We demonstrate how label uncertainty can be extracted from a state-of-the-art object detection system via Dropout Sampling. We evaluate this approach on a large synthetic dataset of 30,000 images, and a real-world dataset captured by a mobile robot in a versatile campus environment. We show that this uncertainty can be utilized to increase object detection performance under the open-set conditions that are typically encountered in robotic vision. A Dropout Sampling network is shown to achieve a 12.3% increase in recall (for the same precision score as a standard network) and a 15.1% increase in precision (for the same recall score as the standard network).