arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1901.01151cs.CV
收藏

从较少的数据中学习:一个统一的计算机视觉数据子集选择和主动学习框架

Learning From Less Data: A Unified Data Subset Selection and Active Learning Framework for Computer Vision

IIT Bombay(印度理工学院孟买分校);Microsoft(微软公司);AITOE Labs(AITOE实验室);University of Massachusetts(马萨诸塞大学)

Vishal Kaushal, Rishabh Iyer, Suraj Kothawade, Rohan Mahadev, Khoshrav Doctor, Ganesh Ramakrishnan

摘要:

基于有监督机器学习的最先进的计算机视觉技术通常需要大量数据。他们的数据整理带来了昂贵的人工标记、计算资源不足和更大的实验周转时间等挑战。训练数据子集选择和主动学习技术已经被提出作为这些挑战的可能解决方案。一类特殊的子集选择函数自然地对多样性、覆盖和表示的概念进行建模,并且可以用于消除冗余,从而很好地用于训练数据子集选择。它们还可以通过选择使用传统的基于不确定性采样的技术获得的示例的子集来帮助提高主动学习的效率,从而进一步减少人类标记工作。在这项工作中,我们经验证明了两个多样性模型的有效性,即设施位置和分散模型的训练数据子集选择和减少标记工作。我们在各种计算机视觉任务中展示了这一点,包括性别识别,人脸识别,场景识别,目标检测和目标识别。我们的研究结果表明,以正确的方式进行基于多样性的子集选择可以提高精度高达5 - 10%,超过现有的基线,特别是在设置中,较少的训练数据是可用的。这允许训练复杂的机器学习模型,如卷积神经网络,其训练数据和标记成本要少得多,同时性能损失最小。

英文摘要:

Supervised machine learning based state-of-the-art computer vision techniques are in general data hungry. Their data curation poses the challenges of expensive human labeling, inadequate computing resources and larger experiment turn around times. Training data subset selection and active learning techniques have been proposed as possible solutions to these challenges. A special class of subset selection functions naturally model notions of diversity, coverage and representation and can be used to eliminate redundancy thus lending themselves well for training data subset selection. They can also help improve the efficiency of active learning in further reducing human labeling efforts by selecting a subset of the examples obtained using the conventional uncertainty sampling based techniques. In this work, we empirically demonstrate the effectiveness of two diversity models, namely the Facility-Location and Dispersion models for training-data subset selection and reducing labeling effort. We demonstrate this across the board for a variety of computer vision tasks including Gender Recognition, Face Recognition, Scene Recognition, Object Detection and Object Recognition. Our results show that diversity based subset selection done in the right way can increase the accuracy by upto 5 - 10% over existing baselines, particularly in settings in which less training data is available. This allows the training of complex machine learning models like Convolutional Neural Networks with much less training data and labeling costs while incurring minimal performance loss.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑