用10%标注数据实现与全监督相当的检测效果，适合路边摄像头场景。
Co-Learning: Towards Semi-Supervised Object Detection with Road-side Cameras
- 师生框架结合互学习与标注对齐，提升未标注数据利用效率。
- 仅用10%标注数据即达到全监督模型性能，显著降低人工标注成本。
- 专为边缘设备优化，适用于真实道路监控等资源受限场景。
近年来，深度学习快速发展，推动了监督学习方法的进步。然而，在现实环境中获取标注数据成本高、耗时长，且常稀缺，这使得神经网络在实际任务中的广泛应用受限，因为为每个应用标注大规模数据不切实际。为此，半监督学习（SSL）通过结合少量标注数据和大量未标注数据训练目标检测器，成为提升检测性能并减少标注成本的可行方案。但现有方法仍面临伪标签不一致、分类与回归任务失衡、以及在边缘设备（如路边摄像头）上高效利用未标注数据等挑战。为此，我们提出一种基于师生架构的半监督学习框架Co-Learning，通过互学习与标注对齐策略有效应对上述问题，在仅使用10%标注数据的情况下，实现了与全监督方法相当的检测性能。
原文摘要 · Abstract (English)
Recently, deep learning has experienced rapid expansion, contributing significantly to the progress of supervised learning methodologies. However, acquiring labeled data in real-world settings can be costly, labor-intensive, and sometimes scarce. This challenge inhibits the extensive use of neural networks for practical tasks due to the impractical nature of labeling vast datasets for every individual application. To tackle this, semi-supervised learning (SSL) offers a promising solution by using both labeled and unlabeled data to train object detectors, potentially enhancing detection efficacy and reducing annotation costs. Nevertheless, SSL faces several challenges, including pseudo-target inconsistencies, disharmony between classification and regression tasks, and efficient use of abundant unlabeled data, especially on edge devices, such as roadside cameras. Thus, we developed a teacher-student-based SSL framework, Co-Learning, which employs mutual learning and annotation-alignment strategies to adeptly navigate these complexities and achieves comparable performance as fully-supervised solutions using 10\% labeled data.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。