Serdar Caglar

TTT-MIM: Test-Time Training with Masked Image Modeling for Denoising Distribution Shifts

"Neural networks trained end-to-end give state-of-the-art performance for image denoising. However, when applied to an image outside of the training distribution, the performance often degrades significantly. In this work, we propose a test-time training (TTT) method based on masked image modeling (…