FisheyePixPro: Self-supervised Pretraining using Fisheye Images for Semantic Segmentation

Ramchandra Cheke, Ganesh Sistu, Ciarán Eising, Pepijn van de Ven, Varun Ravi Kumar, Senthil Yogamani

Research output: Contribution to journalConference articlepeer-review

Abstract

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 pretrain 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.

Original languageEnglish
Article number147
JournalIS and T International Symposium on Electronic Imaging Science and Technology
Volume34
Issue number16
DOIs
Publication statusPublished - 2022
EventIS and T International Symposium on Electronic Imaging: Autonomous Vehicles and Machines, AVM 2022 - Virtual, Online
Duration: 17 Jan 202226 Jan 2022

Fingerprint

Dive into the research topics of 'FisheyePixPro: Self-supervised Pretraining using Fisheye Images for Semantic Segmentation'. Together they form a unique fingerprint.

Cite this