DDFlow: Learning Optical Flow with Unlabeled Data Distillation
Refereed conference paper presented and published in conference proceedings


Full Text

Other information
AbstractWe present DDFlow, a data distillation approach to learningoptical flow estimation from unlabeled data. The approach distills reliable predictions from a teacher network, and uses these predictions as annotations to guide a student networkto learn optical flow. Unlike existing work relying on handcrafted energy terms to handle occlusion, our approach is data-driven, and learns optical flow for occluded pixels. This enables us to train our model with a much simpler loss function, and achieve a much higher accuracy. We conduct a rigorous evaluation on the challenging Flying Chairs, MPI Sintel, KITTI 2012 and 2015 benchmarks, and show that our approach significantly outperforms all existing unsupervised learning methods, while running at real time.
Acceptance Date01/11/2017
All Author(s) ListPengpeng Liu, Irwin King, Michael R.Lyu, Jia Xu
Name of ConferenceThe Thirty-Third AAAI Conference on Artificial Intelligence (AAAI-19)
Start Date of Conference27/01/2019
End Date of Conference01/02/2019
Place of ConferenceHilton Hawaiian Village, Honolulu, Hawaii
Country/Region of ConferenceUnited States of America
Year2019
LanguagesEnglish-United States
KeywordsOptical Flow, CNNs, Unsupervised Learning, Data Distillation

Last updated on 2019-17-10 at 14:26