Learning multi-label scene classification*1

Abstract

In classic pattern recognition problems, classes are mutually exclusive by deÿnition. Classiÿcation errors occur when the classes overlap in the feature space. We examine a di erent situation, occurring when the classes are, by deÿnition, not mutually exclusive. Such problems arise in semantic scene and document classiÿcation and in medical diagnosis. We present a framework to handle such problems and apply it to the problem of semantic scene classiÿcation, where a natural scene may contain multiple objects such that the scene can be described by multiple class labels (e.g., a ÿeld scene with a mountain in the background). Such a problem poses challenges to the classic pattern recognition paradigm and demands a di erent treatment. We discuss approaches for training and testing in this scenario and introduce new metrics for evaluating individual examples, class recall and precision, and overall accuracy. Experiments show that our methods are suitable for scene classiÿcation; furthermore, our work appears to generalize to other classiÿcation problems of the same nature.

GraftNet: An Efficient and Flexible Multi-label Image Classification and Its Application

“…While deep convolutional neural networks (CNNs) have shown a great success in single-label image classification, it is important to note that real world images generally contain multiple labels. Multi-label network classification is a well-known task that is being used in a wide variety of web-based and nonwebbased domains [12] which has achieved great progress due to the development of deep convolutional networks [13]. Although how DCNN best copes with multi-label images still remains an open problem, it has been successfully applied into many real-world applications [14].…”