SIMILAR: Submodular Information Measures Based Active Learning In Realistic Scenarios
It addresses active learning challenges for practitioners dealing with imbalanced or noisy datasets, though it appears incremental as it builds on existing submodular information measures.
The paper tackles the problem of active learning in realistic scenarios like imbalance, rare classes, and out-of-distribution data by proposing SIMILAR, a unified framework using submodular information measures, and shows it outperforms existing methods by 5-18% for rare classes and 5-10% for out-of-distribution data on image classification tasks.
Active learning has proven to be useful for minimizing labeling costs by selecting the most informative samples. However, existing active learning methods do not work well in realistic scenarios such as imbalance or rare classes, out-of-distribution data in the unlabeled set, and redundancy. In this work, we propose SIMILAR (Submodular Information Measures based actIve LeARning), a unified active learning framework using recently proposed submodular information measures (SIM) as acquisition functions. We argue that SIMILAR not only works in standard active learning, but also easily extends to the realistic settings considered above and acts as a one-stop solution for active learning that is scalable to large real-world datasets. Empirically, we show that SIMILAR significantly outperforms existing active learning algorithms by as much as ~5% - 18% in the case of rare classes and ~5% - 10% in the case of out-of-distribution data on several image classification tasks like CIFAR-10, MNIST, and ImageNet. SIMILAR is available as a part of the DISTIL toolkit: "https://github.com/decile-team/distil".