Self-Supervised Learning With Local Contrastive Loss for Detection and Semantic Segmentation

Ashraful Islam, Benjamin Lundell, Harpreet Sawhney, Sudipta N. Sinha, Peter Morales, Richard J. Radke; Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2023, pp. 5624-5633

Abstract

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.

Related Material

[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Islam_2023_WACV, author = {Islam, Ashraful and Lundell, Benjamin and Sawhney, Harpreet and Sinha, Sudipta N. and Morales, Peter and Radke, Richard J.}, title = {Self-Supervised Learning With Local Contrastive Loss for Detection and Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2023}, pages = {5624-5633} }