Domain Adaptive Object Detection via Asymmetric Tri-way Faster-RCNN

Abstract

Conventional object detection models inevitably encounter a performance drop as the domain disparity exists. Unsupervised domain adaptive object detection is proposed recently to reduce the disparity between domains, where the source domain is label-rich while the target domain is label-agnostic. The existing models follow a parameter shared siamese structure for adversarial domain alignment, which, however, easily leads to the collapse and out-of-control risk of the source domain and brings negative impact to feature adaption. The main reason is that the labeling unfairness (asymmetry) between source and target makes the parameter sharing mechanism unable to adapt. Therefore, in order to avoid the source domain collapse risk caused by parameter sharing, we propose an asymmetric tri-way Faster-RCNN (ATF) for domain adaptive object detection. Our ATF model has two distinct merits: 1) A ancillary net supervised by source label is deployed to learn ancillary target features and simultaneously preserve the discrimination of source domain, which enhances the structural discrimination (object classification vs. bounding box regression) of domain alignment. 2) The asymmetric structure consisting of a chief net and an independent ancillary net essentially overcomes the parameter sharing aroused source risk collapse. The adaption safety of the proposed ATF detector is guaranteed. Extensive experiments on a number of datasets, including Cityscapes, Foggy-cityscapes, KITTI, Sim10k, Pascal VOC, Clipart and Watercolor, demonstrate the SOTA performance of our method.

arXiv commentThe paper is accepted in ECCV2020

References in corpus (8)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• YOLOv3: An Incremental Improvement
• DSSD : Deconvolutional Single Shot Detector
• Semantic Foggy Scene Understanding with Synthetic Data
• Unsupervised Domain Adaptation with Residual Transfer Networks
• SCL: Towards Accurate Domain Adaptive Object Detection via Gradient Detach Based Stacked Complementary Losses
• Cascade RPN: Delving into High-Quality Region Proposal Network with Adaptive Convolution
• Unsupervised Domain Adaptation via Structured Prediction Based Selective Pseudo-Labeling

Cited by in corpus (2)

• Domain Adaptive SiamRPN++ for Object Tracking in the Wild
• RPCL: A Framework for Improving Cross-Domain Detection with Auxiliary Tasks