Deep Domain Adaptive Object Detection: a Survey
arXiv:2002.06797
Abstract
Deep learning (DL) based object detection has achieved great progress. These methods typically assume that large amount of labeled training data is available, and training and test data are drawn from an identical distribution. However, the two assumptions are not always hold in practice. Deep domain adaptive object detection (DDAOD) has emerged as a new learning paradigm to address the above mentioned challenges. This paper aims to review the state-of-the-art progress on deep domain adaptive object detection approaches. Firstly, we introduce briefly the basic concepts of deep domain adaptation. Secondly, the deep domain adaptive detectors are classified into five categories and detailed descriptions of representative methods in each category are provided. Finally, insights for future research trend are presented.
arXiv commentAccepted by IEEE SSCI 2020, 6 pages
References in corpus (8)
- Deep Visual Domain Adaptation: A Survey
- Semantic Foggy Scene Understanding with Synthetic Data
- A review of domain adaptation without target labels
- Borrow from Anywhere: Pseudo Multi-modal Object Detection in Thermal Imagery
- SCL: Towards Accurate Domain Adaptive Object Detection via Gradient Detach Based Stacked Complementary Losses
- Domain Adaptation for Object Detection via Style Consistency
- Syn2Real: A New Benchmark forSynthetic-to-Real Visual Domain Adaptation
- Unsupervised Domain Adaptation for Object Detection via Cross-Domain Semi-Supervised Learning
Cited by in corpus (4)
- Multiscale Domain Adaptive YOLO for Cross-Domain Object Detection
- Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer
- Visual Object Recognition in Indoor Environments Using Topologically Persistent Features
- Domain Adaptive Object Detection via Feature Separation and Alignment