EAGER: Large-Scale Distributed Learning of Noisy Labels for Images and Video

这个项目开发了从带有噪声标签的图像和视频中学习的算法。网上免费提供的大量图像和视频给机器学习和计算机视觉研究界带来了前所未有的挑战。它们还带来了巨大的机会和巨大的潜力，可以解决图像理解中的人机语义鸿沟，并彻底改变我们对图像和视频进行索引、检索和交互的方式。不准确的标签和错误标签的数据是图像和视频数据集的常见问题。有噪声的标签会给现有的学习算法带来问题。该项目可以对其他大数据问题产生广泛影响。该项目通过培训学生，确保未被充分代表的群体的广泛参与，以及向公众伸出援手，将该项目与教育相结合。本研究探索了针对带有噪声标签的大规模图像和视频的分布式学习方法。PI研究了具有光滑和非光滑正则项的损失函数的学习问题，并相应地开发了新的分布式学习算法，该算法能够利用过大而不适合单机的丰富的图像。这项研究在图像和视频分析以及计算机视觉应用方面具有巨大的潜力。具体地说，通过(1)开发基于分布式学习的噪声标签优化和学习方法；(2)研究保证收敛、收敛速度和可扩展性等问题，本研究强调了算法和理论两个方面。这项工作为许多领域的新发现提供了广泛适用于许多经济、医学和科学上重要的大规模数据集的新方法。

This project develops algorithms for learning from images and video with noisy labels. The overwhelming amounts of images and video freely available online present unprecedented challenges for machine learning and computer vision research communities. They also bring tremendous opportunities and great potentials for addressing human-machine semantic gaps in image understanding and for revolutionizing our ways to index, retrieve, and interact with images and video. Inaccurate labels and mislabeled data are common problems for image and video datasets. Noisy labels would cause problems with the existing learning algorithms. This project can have broad impacts on other big data problem. The project is integrated with education by training students, ensuring broad participation of underrepresented groups, and outreaching general public.This research exploring distributed learning methods for large-scale images and video with noisy labels. The PI investigates the learning problem of loss functions with both smooth and non-smooth regularization terms, and accordingly develops new distributed learning algorithms that are capable of leveraging the abundance of images that are too large to fit into a single machine. The research has an immense potential in image and video analysis, and computer vision applications. Specifically, this research emphasizes both algorithmic and theoretic aspects by (1) developing distributed learning based approaches for optimization and learning of noisy labels; and (2) investigating issues such as guaranteed convergence, convergence rate, and scalability. This work provides new methods that are widely applicable to many economically, medically and scientifically important large-scale datasets for novel discoveries across many domains.