Deeply Aligned Adaptation for Cross-domain Object Detection
arXiv:2004.02093
Abstract
Cross-domain object detection has recently attracted more and more attention for real-world applications, since it helps build robust detectors adapting well to new environments. In this work, we propose an end-to-end solution based on Faster R-CNN, where ground-truth annotations are available for source images (e.g., cartoon) but not for target ones (e.g., watercolor) during training. Motivated by the observation that the transferabilities of different neural network layers differ from each other, we propose to apply a number of domain alignment strategies to different layers of Faster R-CNN, where the alignment strength is gradually reduced from low to higher layers. Moreover, after obtaining region proposals in our network, we develop a foreground-background aware alignment module to further reduce the domain mismatch by separately aligning features of the foreground and background regions from the source and target domains. Extensive experiments on benchmark datasets demonstrate the effectiveness of our proposed approach.
References in corpus (8)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- How transferable are features in deep neural networks?
- Deep Domain Confusion: Maximizing for Domain Invariance
- Deep Visual Domain Adaptation: A Survey
- Semantic Foggy Scene Understanding with Synthetic Data
- Unsupervised Domain Adaptation with Residual Transfer Networks
- Wasserstein Distance Based Domain Adaptation for Object Detection