University of Limerick
Browse
FisheyePixPro__Self_supervised_Pretraining_using_Fisheye_Images_for_Semantic_Segmentation.pdf (26.23 MB)

FisheyePixPro: self-supervised pretraining using fisheye images for semantic segmentation

Download (26.23 MB)
conference contribution
posted on 2022-03-16, 12:02 authored by Ramchandra Cheke, Ganesh Sistu, Ciarán Eising, Pepijn van de Ven, Varun Ravi Kumar, Senthil Yogamani
Self-supervised learning has been an active area of research in the past few years. Contrastive learning is a type of self-supervised learning method that has achieved a significant performance improvement on image classification task. However, there has been no work done in its application to fisheye images for autonomous driving. In this paper, we propose FisheyePixPro, which is an adaption of pixel level contrastive learning method PixPro [1] for fisheye images. This is the first attempt to pre-train a contrastive learning based model, directly on fisheye images in a self-supervised approach. We evaluate the performance of learned representations on the WoodScape dataset using segmentation task. Our FisheyePixPro model achieves a 65.78 mIoU score, a significant improvement over the PixPro model. This indicates that pre-training a model on fisheye images have a better performance on a downstream task.

History

Publication

Electronic Imaging, Autonomous Vehicles and Machines Conference 2022;

Note

peer-reviewed

Other Funding information

SFI, Irish Centre for High-End Computing (ICHEC)

Language

English

Usage metrics

    University of Limerick

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC