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

TL;DR

This survey reviews 27 recent advancements in semi-supervised object detection, highlighting progress from CNNs to Transformers, and discusses techniques, challenges, and future research directions in reducing reliance on labeled data.

Contribution

The paper provides a comprehensive overview of recent SSOD methods, comparing architectures and techniques from CNNs to Transformers, and identifies key challenges and future research directions.

Findings

Significant performance improvements in SSOD models.

Effective strategies for pseudo-labeling and data augmentation.

Transition from CNN-based to Transformer-based architectures.

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.