Domain Adaptive Faster R-CNN for Object Detection in the Wild

TL;DR

This paper introduces a domain adaptive Faster R-CNN that improves object detection robustness across different domains by reducing image-level and instance-level discrepancies through adversarial training and consistency regularization.

Contribution

It proposes a novel domain adaptation framework for Faster R-CNN that addresses both image and instance level shifts using adversarial learning and consistency regularization.

Findings

Significant performance improvements on Cityscapes, KITTI, and SIM10K datasets.

Effective reduction of domain discrepancy at multiple levels.

Enhanced robustness of object detection in diverse domain shift scenarios.

Abstract

Object detection typically assumes that training and test data are drawn from an identical distribution, which, however, does not always hold in practice. Such a distribution mismatch will lead to a significant performance drop. In this work, we aim to improve the cross-domain robustness of object detection. We tackle the domain shift on two levels: 1) the image-level shift, such as image style, illumination, etc, and 2) the instance-level shift, such as object appearance, size, etc. We build our approach based on the recent state-of-the-art Faster R-CNN model, and design two domain adaptation components, on image level and instance level, to reduce the domain discrepancy. The two domain adaptation components are based on H-divergence theory, and are implemented by learning a domain classifier in adversarial training manner. The domain classifiers on different levels are further reinforced with a consistency regularization to learn a domain-invariant region proposal network (RPN) in the Faster R-CNN model. We evaluate our newly proposed approach using multiple datasets including Cityscapes, KITTI, SIM10K, etc. The results demonstrate the effectiveness of our proposed approach for robust object detection in various domain shift scenarios.