English

Semi-Supervised Object Detection: A Survey on Progress from CNN to Transformer

Computer Vision and Pattern Recognition 2024-07-17 v2

Abstract

The impressive advancements in semi-supervised learning have driven researchers to explore its potential in object detection tasks within the field of computer vision. Semi-Supervised Object Detection (SSOD) leverages a combination of a small labeled dataset and a larger, unlabeled dataset. This approach effectively reduces the dependence on large labeled datasets, which are often expensive and time-consuming to obtain. Initially, SSOD models encountered challenges in effectively leveraging unlabeled data and managing noise in generated pseudo-labels for unlabeled data. However, numerous recent advancements have addressed these issues, resulting in substantial improvements in SSOD performance. This paper presents a comprehensive review of 27 cutting-edge developments in SSOD methodologies, from Convolutional Neural Networks (CNNs) to Transformers. We delve into the core components of semi-supervised learning and its integration into object detection frameworks, covering data augmentation techniques, pseudo-labeling strategies, consistency regularization, and adversarial training methods. Furthermore, we conduct a comparative analysis of various SSOD models, evaluating their performance and architectural differences. We aim to ignite further research interest in overcoming existing challenges and exploring new directions in semi-supervised learning for object detection.

Keywords

Cite

@article{arxiv.2407.08460,
  title  = {Semi-Supervised Object Detection: A Survey on Progress from CNN to Transformer},
  author = {Tahira Shehzadi and Ifza and Didier Stricker and Muhammad Zeshan Afzal},
  journal= {arXiv preprint arXiv:2407.08460},
  year   = {2024}
}
R2 v1 2026-06-28T17:37:17.928Z