# Test-Time Modification: Inverse Domain Transformation for Robust Perception Source: [Test-Time Modification: Inverse Domain Transformation for Robust Perception]() Collection index: [llms.txt]() Data updated: 2026-03-28T05:00:04.913Z Authors: Arpit Jadon, Joshua Niemeijer, Yuki M. Asano Published: 2025-12-15T15:51:30.000Z ## Abstract Generative foundation models contain broad visual knowledge and can produce diverse image variations, making them particularly promising for advancing domain generalization tasks. They can be used for training data augmentation, but synthesizing comprehensive target-domain variations remains slow, expensive, and incomplete. We propose an alternative: using diffusion models at test time to map target images back to the source distribution where the downstream model was trained. This approach requires only a source domain description, preserves the task model, and eliminates large-scale synthetic data generation. We demonstrate consistent improvements across segmentation, detection, and classification tasks under challenging environmental shifts in real-to-real domain generalization scenarios with unknown target distributions. Our analysis spans multiple generative and downstream models, including an ensemble variant for enhanced robustness. The method improves BDD100K-Night-Det mAP@50 from 10.2 to 31.8, ImageNet-R top-1 from 36.1 to 60.8, and DarkZurich mIoU from 28.6 to 46.3. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Image Classification on ImageNet-R](): Image Classification; ImageNet-R; Top-1 Acc: 63.5. ## Original sources and implementation [Original paper]() [PDF]()