Reproducibility of "FDA: Fourier Domain Adaptation forSemantic Segmentation
This work verifies the reproducibility of a domain adaptation technique for computer vision researchers, which is incremental as it replicates prior findings.
The paper reproduces the FDA method for semantic segmentation domain adaptation, confirming the original results with a 1.5% mIoU improvement on the GTA5 to Cityscapes benchmark.
The following paper is a reproducibility report for "FDA: Fourier Domain Adaptation for Semantic Segmentation" published in the CVPR 2020 as part of the ML Reproducibility Challenge 2020. The original code was made available by the author. The well-commented version of the code containing all ablation studies performed derived from the original code along with WANDB integration is available at <github.com/thefatbandit/FDA> with proper instructions to execute experiments in README.