Segment scene in new domain with one image using adversarial refinement with SITTA-SEG
Segment scene in new domain with one image using adversarial refinement with SITTA-SEG
Single Image Test-Time Adaptation for Segmentation
arXiv paper abstract https://arxiv.org/abs/2309.14052
arXiv PDF paper https://arxiv.org/pdf/2309.14052.pdf
Project page https://klarajanouskova.github.io/sitta-seg
Test-Time Adaptation (TTA) methods improve the robustness of deep neural networks to domain shift on a variety of tasks such as image classification or segmentation.
This work explores adapting segmentation models to a single unlabelled image with no other data available at test-time.
In particular, this work focuses on adaptation by optimizing self-supervised losses at test-time.
Multiple baselines based on different principles are evaluated under diverse conditions and a novel adversarial training is introduced for adaptation with mask refinement.
... additions to the baselines result in a 3.51 and 3.28 % increase over non-adapted baselines, without these improvements, the increase would be 1.7 and 2.16 % only.
Please like and share this post if you enjoyed it using the buttons at the bottom!
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
Comments