FDA: Fourier Domain Adaptation for Semantic Segmentation
This addresses the problem of adapting models from synthetic to real data in semantic segmentation, offering a simpler alternative to complex adversarial methods.
The paper tackles unsupervised domain adaptation for semantic segmentation by swapping low-frequency Fourier spectra between source and target domains, achieving state-of-the-art performance without requiring training for domain alignment.
We describe a simple method for unsupervised domain adaptation, whereby the discrepancy between the source and target distributions is reduced by swapping the low-frequency spectrum of one with the other. We illustrate the method in semantic segmentation, where densely annotated images are aplenty in one domain (synthetic data), but difficult to obtain in another (real images). Current state-of-the-art methods are complex, some requiring adversarial optimization to render the backbone of a neural network invariant to the discrete domain selection variable. Our method does not require any training to perform the domain alignment, just a simple Fourier Transform and its inverse. Despite its simplicity, it achieves state-of-the-art performance in the current benchmarks, when integrated into a relatively standard semantic segmentation model. Our results indicate that even simple procedures can discount nuisance variability in the data that more sophisticated methods struggle to learn away.