Zapisane w:
Opis bibliograficzny
Główni autorzy: Kothandaraman, Divya, Chandra, Rohan, Manocha, Dinesh
Format: Preprint
Wydane: 2020
Hasła przedmiotowe:
Dostęp online:https://arxiv.org/abs/2012.08939
Etykiety: Dodaj etykietę
Nie ma etykietki, Dołącz pierwszą etykiete!
Spis treści:
  • We present a novel approach for unsupervised road segmentation in adverse weather conditions such as rain or fog. This includes a new algorithm for source-free domain adaptation (SFDA) using self-supervised learning. Moreover, our approach uses several techniques to address various challenges in SFDA and improve performance, including online generation of pseudo-labels and self-attention as well as use of curriculum learning, entropy minimization and model distillation. We have evaluated the performance on $6$ datasets corresponding to real and synthetic adverse weather conditions. Our method outperforms all prior works on unsupervised road segmentation and SFDA by at least 10.26%, and improves the training time by 18-180x. Moreover, our self-supervised algorithm exhibits similar accuracy performance in terms of mIOU score as compared to prior supervised methods.