We present a self-supervised learning (SSL) method suitable for semi-global tasks such as object detection and semantic segmentation. We enforce local consistency between self-learned features, representing corresponding image locations of transformed versions of the same image, by minimizing a pixel-level local contrastive (LC) loss during training. LC-loss can be added to existing self-supervised learning methods with minimal overhead. We evaluate our SSL approach on two downstream tasks -- object detection and semantic segmentation, using COCO, PASCAL VOC, and CityScapes datasets. Our method outperforms the existing state-of-the-art SSL approaches by 1.9% on COCO object detection, 1.4% on PASCAL VOC detection, and 0.6% on CityScapes segmentation.
@article{arxiv.2207.04398,
title = {Self-supervised Learning with Local Contrastive Loss for Detection and Semantic Segmentation},
author = {Ashraful Islam and Ben Lundell and Harpreet Sawhney and Sudipta Sinha and Peter Morales and Richard J. Radke},
journal= {arXiv preprint arXiv:2207.04398},
year = {2022}
}