Papers
arxiv:2508.01966

Self-Supervised YOLO: Leveraging Contrastive Learning for Label-Efficient Object Detection

Published on Aug 4
Authors:
,
,

Abstract

Contrastive self-supervised learning (SSL) using SimCLR framework pretrains YOLOv5 and YOLOv8 backbones on unlabeled images, improving their performance in object detection tasks with limited labeled data.

AI-generated summary

One-stage object detectors such as the YOLO family achieve state-of-the-art performance in real-time vision applications but remain heavily reliant on large-scale labeled datasets for training. In this work, we present a systematic study of contrastive self-supervised learning (SSL) as a means to reduce this dependency by pretraining YOLOv5 and YOLOv8 backbones on unlabeled images using the SimCLR framework. Our approach introduces a simple yet effective pipeline that adapts YOLO's convolutional backbones as encoders, employs global pooling and projection heads, and optimizes a contrastive loss using augmentations of the COCO unlabeled dataset (120k images). The pretrained backbones are then fine-tuned on a cyclist detection task with limited labeled data. Experimental results show that SSL pretraining leads to consistently higher mAP, faster convergence, and improved precision-recall performance, especially in low-label regimes. For example, our SimCLR-pretrained YOLOv8 achieves a mAP@50:95 of 0.7663, outperforming its supervised counterpart despite using no annotations during pretraining. These findings establish a strong baseline for applying contrastive SSL to one-stage detectors and highlight the potential of unlabeled data as a scalable resource for label-efficient object detection.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2508.01966 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2508.01966 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2508.01966 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.