Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Semi-Supervised Learning of Optical Flow by Flow Supervisor

About

A training pipeline for optical flow CNNs consists of a pretraining stage on a synthetic dataset followed by a fine tuning stage on a target dataset. However, obtaining ground truth flows from a target video requires a tremendous effort. This paper proposes a practical fine tuning method to adapt a pretrained model to a target dataset without ground truth flows, which has not been explored extensively. Specifically, we propose a flow supervisor for self-supervision, which consists of parameter separation and a student output connection. This design is aimed at stable convergence and better accuracy over conventional self-supervision methods which are unstable on the fine tuning task. Experimental results show the effectiveness of our method compared to different self-supervision methods for semi-supervised learning. In addition, we achieve meaningful improvements over state-of-the-art optical flow models on Sintel and KITTI benchmarks by exploiting additional unlabeled datasets. Code is available at https://github.com/iwbn/flow-supervisor.

Woobin Im, Sebin Lee, Sung-Eui Yoon• 2022

Related benchmarks

TaskDatasetResultRank
Optical FlowSintel (test)
AEPE (Final)2.79
120
Optical FlowSintel Final (train)
EPE2.46
92
Optical FlowSintel Clean (train)
EPE1.3
85
Optical FlowKITTI (train)
Fl-all0.159
63
Optical FlowKITTI (test)--
28
Optical Flow EstimationKITTI (test)
F1-all4.85
20
Showing 6 of 6 rows

Other info

Follow for update