用主动学习选关键图像，减少训练数据量
Active Learning for Multi-class Image Classification
- 根据不确定性指标挑选最有价值的图像用于训练
- 在MNIST和Fruits360上显著降低所需标注样本数
- 对复杂多分类任务效果更明显，适合数据稀缺场景
图像分类面临训练样本数量庞大的瓶颈。通过主动学习，可基于策略性选择样本，减少训练CNN分类器所需的标注数据量。利用不同不确定性度量为图像分配价值，使模型能在更小训练集下识别并选取高价值样本。我们在MNIST和Fruits360数据集上验证了数字识别与水果分类任务的效果，并正式比较了四种不确定性度量的性能。结果表明，主动学习在简单二分类任务中有效，但对更复杂的分类任务，相比随机采样有显著提升。这证明主动学习是图像分类问题的一种可行方案。
原文摘要 · Abstract (English)
A principle bottleneck in image classification is the large number of training examples needed to train a classifier. Using active learning, we can reduce the number of training examples to teach a CNN classifier by strategically selecting examples. Assigning values to image examples using different uncertainty metrics allows the model to identify and select high-value examples in a smaller training set size. We demonstrate results for digit recognition and fruit classification on the MNIST and Fruits360 data sets. We formally compare results for four different uncertainty metrics. Finally, we observe active learning is also effective on simpler (binary) classification tasks, but marked improvement from random sampling is more evident on more difficult tasks. We show active learning is a viable algorithm for image classification problems.
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。