MVCAL: Multi View Clustering for Active Learning

Yi Fan, Biao Jiang, Di Chen, Yu-Bin Yang

Abstract: Various active learning methods with ingenious sampling strategies have been proposed to solve the lack of labeled samples in supervised learning, but most are designed for specific tasks. In this paper, we propose a simple but task-agnostic active sampling method. We introduce ‘multi-view clustering module’ to extract multiple feature maps at different levels for unsupervised clustering. According to clustering distribution, we calculate consistency, representativeness and stability to guide sampling and training. Among them, consistency measures the similarity between clustering results of two views, representativeness reflects the distance between a sample and the corresponding cluster center, and stability reflects the model’s feature representation and recognition ability for the same sample. Our method does not depend on the specific network, and can be constructed as a two-stage sampling module to supplement the existing sampling algorithm. Experiments results on image classification and object detection tasks show that our method can further enhance the effect of active learning on the basis of baseline methods.