论文标题
一位监督图像分类
One-bit Supervision for Image Classification
论文作者
论文摘要
本文在图像分类的情况下介绍了一位监督，这是一种从不完整注释中学习的新颖设置。我们的设置没有在每个样本的准确标签上训练模型，而是需要使用每个样本的预测标签查询，并从答案中学习猜测是否正确。这提供了一位（是或否）的信息，更重要的是，注释每个样本比从许多候选类别中找到准确的标签要容易得多。一位监督对训练模型有两个关键：提高猜测准确性并利用不正确的猜测。为了这些目的，我们提出了一个多阶段训练范式，将负标签抑制纳入现成的半监督学习算法中。在三个流行的图像分类基准中，我们的方法声称在利用有限的注释方面提高了效率。
This paper presents one-bit supervision, a novel setting of learning from incomplete annotations, in the scenario of image classification. Instead of training a model upon the accurate label of each sample, our setting requires the model to query with a predicted label of each sample and learn from the answer whether the guess is correct. This provides one bit (yes or no) of information, and more importantly, annotating each sample becomes much easier than finding the accurate label from many candidate classes. There are two keys to training a model upon one-bit supervision: improving the guess accuracy and making use of incorrect guesses. For these purposes, we propose a multi-stage training paradigm which incorporates negative label suppression into an off-the-shelf semi-supervised learning algorithm. In three popular image classification benchmarks, our approach claims higher efficiency in utilizing the limited amount of annotations.
