首页|Research on Artificial Intelligence Detailed by Researchers at Ben- Gurion Univer sity of the Negev (Semi-supervised active learning using convolutional auto- enc oder and contrastive learning)
Research on Artificial Intelligence Detailed by Researchers at Ben- Gurion Univer sity of the Negev (Semi-supervised active learning using convolutional auto- enc oder and contrastive learning)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on artificial intelligenc e is the subject of a new report. According to news reporting from Be'er Sheva, Israel, by NewsRx journalists, research stated, "Active learning is a field of m achine learning that seeks to find the most efficient labels to annotate with a given budget, particularly in cases where obtaining labeled data is expensive or infeasible. This is becoming increasingly important with the growing success of learning-based methods, which often require large amounts of labeled data." The news reporters obtained a quote from the research from Ben-Gurion University of the Negev: "Computer vision is one area where active learning has shown prom ise in tasks such as image classification, semantic segmentation, and object det ection. In this research, we propose a pool-based semi-supervised active learnin g method for image classification that takes advantage of both labeled and unlab eled data. Many active learning approaches do not utilize unlabeled data, but we believe that incorporating these data can improve performance. To address this issue, our method involves several steps. First, we cluster the latent space of a pre-trained convolutional autoencoder. Then, we use a proposed clustering cont rastive loss to strengthen the latent space's clustering while using a small amo unt of labeled data. Finally, we query the samples with the highest uncertainty to annotate with an oracle. We repeat this process until the end of the given bu dget."
Ben-Gurion University of the NegevBe'e r ShevaIsraelAsiaArtificial IntelligenceMachine Learning
NETL
NSTL
