HIERMATCH: Leveraging Label Hierarchies for Improving Semi-Supervised Learning
This addresses the challenge of high annotation costs for researchers and practitioners in machine learning, though it is an incremental improvement over existing semi-supervised methods.
The paper tackles the problem of reducing labeling costs in semi-supervised learning by proposing HIERMATCH, a framework that leverages hierarchical label information, such as coarse labels, to improve performance; it reduces fine-grained label usage by 50% on CIFAR-100 with only a 0.59% drop in accuracy compared to MixMatch.
Semi-supervised learning approaches have emerged as an active area of research to combat the challenge of obtaining large amounts of annotated data. Towards the goal of improving the performance of semi-supervised learning methods, we propose a novel framework, HIERMATCH, a semi-supervised approach that leverages hierarchical information to reduce labeling costs and performs as well as a vanilla semi-supervised learning method. Hierarchical information is often available as prior knowledge in the form of coarse labels (e.g., woodpeckers) for images with fine-grained labels (e.g., downy woodpeckers or golden-fronted woodpeckers). However, the use of supervision using coarse category labels to improve semi-supervised techniques has not been explored. In the absence of fine-grained labels, HIERMATCH exploits the label hierarchy and uses coarse class labels as a weak supervisory signal. Additionally, HIERMATCH is a generic-approach to improve any semisupervised learning framework, we demonstrate this using our results on recent state-of-the-art techniques MixMatch and FixMatch. We evaluate the efficacy of HIERMATCH on two benchmark datasets, namely CIFAR-100 and NABirds. HIERMATCH can reduce the usage of fine-grained labels by 50% on CIFAR-100 with only a marginal drop of 0.59% in top-1 accuracy as compared to MixMatch. Code: https://github.com/07Agarg/HIERMATCH