Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2508.01966 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912518088163328 |
|---|---|
| author | Kotthapalli, Manikanta Bhatia, Reshma Jain, Nainsi |
| author_facet | Kotthapalli, Manikanta Bhatia, Reshma Jain, Nainsi |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_01966 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Self-Supervised YOLO: Leveraging Contrastive Learning for Label-Efficient Object Detection Kotthapalli, Manikanta Bhatia, Reshma Jain, Nainsi Computer Vision and Pattern Recognition 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. |
| title | Self-Supervised YOLO: Leveraging Contrastive Learning for Label-Efficient Object Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.01966 |