Unsupervised Image-to-Image Translation with Patch Pyramid Dual Contrastive Learning for Cross Domain Object Detection

Unsupervised image-to-image (UI2I) translation methods aim to learn a mapping between different visual domains with well-preserved content and consistent structure. It has been proven that the generated images are useful for enhancing the performance of computer vision tasks like object detection in a different domain with distribution discrepancies. Current UI2I translation techniques are highly relied on cycle-structure consistency and content/style disentanglement. In-tense focus has been paid on global translation over an en-tire image, instead of the stylistic variations and complex structure among multiple disparate object instances and back-grounds, resulting in unsatisfactory performance gain for the downstream vision tasks. In this work, we propose Patch Pyramid Dual Contrastive Learning Unsupervised Image Translation (PPDCLUIT) framework to strengthen the cross domain object detection performance. We present patch pyra-mid dual contrastive learning strategy for coherent associations at each specific location and propose identity loss to further enforce the object instances preservation. We im-plement extensive experiments to demonstrate the efficacy of our PPDCLUIT framework for cross domain object detection and achieve state-of-the-art performance on the benchmarks of Normal-to-Foggy, and Day-to-Night.