Unsupervised Domain Adaptation of Object Detectors: A Survey

Recent advances in deep learning have led to the development of accurate and efficient models for various computer vision applications such as classification, segmentation, and detection. However, learning highly accurate models relies on the availability of large-scale annotated datasets. Due to this, model performance drops drastically when evaluated on label-scarce datasets having visually distinct images, termed as domain adaptation problem. There are a plethora of works to adapt classification and segmentation models to label-scarce target dataset through unsupervised domain adaptation. Considering that detection is a fundamental task in computer vision, many recent works have focused on developing novel domain adaptive detection techniques. Here, we describe in detail the domain adaptation problem for detection and present an extensive survey of the various methods. Furthermore, we highlight strategies proposed and the associated shortcomings. Subsequently, we identify multiple aspects of the problem that are most promising for future research. We believe that this survey shall be valuable to the pattern recognition experts working in the fields of computer vision, biometrics, medical imaging, and autonomous navigation by introducing them to the problem, and familiarizing them with the current status of the progress while providing promising directions for future research.

I. Introduction

The success of deep learning has been greatly beneficial for various fields such as natural language processing [1], [2], [3], robotics [4], [5], [6], computer vision [7], [8], [9], etc. This is especially evident in the case of computer vision, where majority of the progress can be largely attributed to the advancements in deep convolutional neural networks (DCNN) [7]. Owing to their learning capacity, DCNN models have achieved state-of-the-art performance in many vision tasks such as object classification ([9], [10], [11]), semantic segmentation ([12], [13], [14]), and object detection ([15], [16], [17]). This has led to DCNN's increased popularity in several real world applications as compared to the classical computer vision techniques. Specifically, deep learning based object detection has become an integral part of many real-world applications ranging from video security/surveillance, augmented reality, autonomous navigation, human computer interface, self-checkout convenience stores. Major advancements like Faster-RCNN [15], You Only Look Once (YOLO) [16] and Single Shot Multi-box Detector (SSD) [17] have resulted in significant improvements of detection performance and speed.