Rebalancing gradient to improve self-supervised co-training of depth, odometry and optical flow predictions

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

We present CoopNet, an approach that improves the co-operation of co-trained networks by dynamically adapting the apportionment of gradient, to ensure equitable learning progress. It is applied to motion-aware self-supervised prediction of depth maps, by introducing a new hybrid loss, based on a distribution model of photo-metric reconstruction errors made by, on the one hand the depth + odometry paired networks, and on the other hand the optical flow network. This model essentially assumes that the pixels from moving objects (that must be discarded for training depth and odometry), correspond to those where the two reconstructions strongly disagree. We justify this model by theoretical considerations and experimental evidences. A comparative evaluation on KITTI and CityScapes datasets shows that CoopNet improves or is comparable to the state-of-the-art in depth, odometry and optical flow predictions. Our code is available here: https://github.com/mhariat/CoopNet.

Original languageEnglish
Title of host publicationProceedings - 2023 IEEE Winter Conference on Applications of Computer Vision, WACV 2023
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1267-1276
Number of pages10
ISBN (Electronic)9781665493468
DOIs
Publication statusPublished - 1 Jan 2023
Externally publishedYes
Event23rd IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2023 - Waikoloa, United States
Duration: 3 Jan 20237 Jan 2023

Publication series

NameProceedings - 2023 IEEE Winter Conference on Applications of Computer Vision, WACV 2023

Conference

Conference23rd IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2023
Country/TerritoryUnited States
CityWaikoloa
Period3/01/237/01/23

Keywords

  • 3D computer vision
  • Algorithms: Image recognition and understanding (object detection, categorization, segmentation)
  • Machine learning architectures
  • and algorithms (including transfer, low-shot, semi-, self-, and un-supervised learning)
  • formulations

Fingerprint

Dive into the research topics of 'Rebalancing gradient to improve self-supervised co-training of depth, odometry and optical flow predictions'. Together they form a unique fingerprint.

Cite this