Randomized Spectrum Transformations for Adapting Object Detector in Unseen Domains

We propose a Meta Learning on Randomized Transformations (MLRT) to learn domain invariant object detectors. Domain generalization is a problem about learning an invariant model from multiple source domains which can generalize well on unseen target domains. This problem is overlooked in object detection field, which is formally named as domain generalizable object detection (DGOD). Moreover, existing domain generalization methods have the problem of domain bias so that they can easily overfit to some specific domain (e.g., source domain). In order to alleviate the domain bias, in MLRT model, a novel randomized spectrum transformation (RST) module is proposed to increase the diversity of source domains. Specifically, RST randomizes the domain specific information of images in frequency-space, which can transform single or multiple source domains into various new domains. Besides, we observe a prior that the gradient imbalance degree among domains can also reflect the domain bias. Therefore, we further propose to alleviate the domain bias from the perspective of gradient balancing, and a novel gradient weighting (GW) module is proposed to balance the gradients over all domains via a hand-crafted weight. Finally we embed our RST and GW into a general meta learning framework and the proposed MLRT model is formalized for DGOD task. Extensive experiments are conducted on six benchmarks, and our method achieves the SOTA performance.

Automated summary

We propose a meta learning method based on randomized transformations to learn domain invariant object detectors. The method addresses the problem of domain bias in domain generalizable object detection by increasing the diversity of source domains and balancing the gradients among different domains. Experimental results on multiple benchmarks demonstrate that our method achieves state-of-the-art performance.