TY - JOUR
T1 - FisheyePixPro
T2 - IS and T International Symposium on Electronic Imaging: Autonomous Vehicles and Machines, AVM 2022
AU - Cheke, Ramchandra
AU - Sistu, Ganesh
AU - Eising, Ciarán
AU - van de Ven, Pepijn
AU - Kumar, Varun Ravi
AU - Yogamani, Senthil
N1 - Publisher Copyright:
© 2022, Society for Imaging Science and Technology.
PY - 2022
Y1 - 2022
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85130135158&partnerID=8YFLogxK
U2 - 10.2352/EI.2022.34.16.AVM-147
DO - 10.2352/EI.2022.34.16.AVM-147
M3 - Conference article
AN - SCOPUS:85130135158
SN - 2470-1173
VL - 34
JO - IS and T International Symposium on Electronic Imaging Science and Technology
JF - IS and T International Symposium on Electronic Imaging Science and Technology
IS - 16
M1 - 147
Y2 - 17 January 2022 through 26 January 2022
ER -