Unsupervised Cross-domain Object Detection Based on Progressive Multi-source Transfer

To address the difficulty of collecting manually labeled training samples for object detection tasks, this paper proposes an unsupervised cross-domain object detection method that gradually adapts the model at pixel level and feature level. The existing pixel-level domain adaptive methods generate translated images with a single style and inconsistent content structure. To solve this problem, this paper embeds the input images into domain-invariant content space and domain-specific attribute space, then cooperates different space representations to synthesize diverse translated images that preserve the spatial semantic information to enable label transfer. In addition, for feature-level domain adaptation, to alleviate the source-bias problem caused by single source domain, we treat the generated diverse labeled images as source domain data and design a multi-domain discriminator to get multi-domain-invariant representations. Finally, To further enhance the detection performance on the target domain, we propose a self-training framework to alternatively generate pseudo labels on target training data. The exploratory experiment results from the Cityscapes & Foggy Cityscapes dataset and VOC07 & Clipart1k dataset demonstrate that compared with the current unsupervised cross-domain detection methods, the proposed detection framework achieves better transferability. © 2022 Science Press. All rights reserved.