FusionNet and AugmentedFlowNet: Selective Proxy Ground Truth for Training on Unlabeled Images

08/20/2018
by   Osama Makansi, et al.
0

Recent work has shown that convolutional neural networks (CNNs) can be used to estimate optical flow with high quality and fast runtime. This makes them preferable for real-world applications. However, such networks require very large training datasets. Engineering the training data is difficult and/or laborious. This paper shows how to augment a network trained on an existing synthetic dataset with large amounts of additional unlabelled data. In particular, we introduce a selection mechanism to assemble from multiple estimates a joint optical flow field, which outperforms that of all input methods. The latter can be used as proxy-ground-truth to train a network on real-world data and to adapt it to specific domains of interest. Our experimental results show that the performance of networks improves considerably, both, in cross-domain and in domain-specific scenarios. As a consequence, we obtain state-of-the-art results on the KITTI benchmarks.

READ FULL TEXT

page 9

page 13

research
11/21/2017

UnFlow: Unsupervised Learning of Optical Flow with a Bidirectional Census Loss

In the era of end-to-end deep learning, many advances in computer vision...
research
09/21/2018

Temporal Interpolation as an Unsupervised Pretraining Task for Optical Flow Estimation

The difficulty of annotating training data is a major obstacle to using ...
research
02/08/2017

Guided Optical Flow Learning

We study the unsupervised learning of CNNs for optical flow estimation u...
research
04/08/2021

Learning optical flow from still images

This paper deals with the scarcity of data for training optical flow net...
research
07/21/2022

Semi-Supervised Learning of Optical Flow by Flow Supervisor

A training pipeline for optical flow CNNs consists of a pretraining stag...
research
03/11/2019

Demonstration of Vector Flow Imaging using Convolutional Neural Networks

Synthetic Aperture Vector Flow Imaging (SA-VFI) can visualize complex ca...
research
10/01/2019

Learning to estimate label uncertainty for automatic radiology report parsing

Bootstrapping labels from radiology reports has become the scalable alte...

Please sign up or login with your details

Forgot password? Click here to reset