no code implementations • CVPR 2022 • Juwon Kang, Sohyun Lee, Namyup Kim, Suha Kwak
Existing methods in this direction suppose that a domain can be characterized by styles of its images, and train a network using style-augmented data so that the network is not biased to particular style distributions.
1 code implementation • 17 Jul 2020 • Taeyoung Son, Juwon Kang, Namyup Kim, Sunghyun Cho, Suha Kwak
Despite the great advances in visual recognition, it has been witnessed that recognition models trained on clean images of common datasets are not robust against distorted images in the real world.