Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Efficient Diffusion-Driven Corruption Editor for Test-Time Adaptation

About

Test-time adaptation (TTA) addresses the unforeseen distribution shifts occurring during test time. In TTA, performance, memory consumption, and time consumption are crucial considerations. A recent diffusion-based TTA approach for restoring corrupted images involves image-level updates. However, using pixel space diffusion significantly increases resource requirements compared to conventional model updating TTA approaches, revealing limitations as a TTA method. To address this, we propose a novel TTA method that leverages an image editing model based on a latent diffusion model (LDM) and fine-tunes it using our newly introduced corruption modeling scheme. This scheme enhances the robustness of the diffusion model against distribution shifts by creating (clean, corrupted) image pairs and fine-tuning the model to edit corrupted images into clean ones. Moreover, we introduce a distilled variant to accelerate the model for corruption editing using only 4 network function evaluations (NFEs). We extensively validated our method across various architectures and datasets including image and video domains. Our model achieves the best performance with a 100 times faster runtime than that of a diffusion-based baseline. Furthermore, it is three times faster than the previous model updating TTA method that utilizes data augmentation, making an image-level updating approach more feasible.

Yeongtak Oh, Jonghyun Lee, Jooyoung Choi, Dahuin Jung, Uiwon Hwang, Sungroh Yoon• 2024

Related benchmarks

TaskDatasetResultRank
Vision-Language NavigationR2R Continuous Environments (test)
SR (Gaussian)28.53
5
Temporal consistency evaluationR2R-CE (test)
Warp Error (Gaussian)0.15
5
Temporal consistency evaluationRxR-CE (test)
Warp Error (Gaussian)0.16
5
Vision-Language NavigationRxR-CE Continuous Environments (test)
Success Rate (Gaussian Noise)29.74
5
Vision-Language NavigationR2R-CE and RxR-CE
Inference Time (ms)370
4
Showing 5 of 5 rows

Other info

Follow for update