A Unified Approach Towards Active Learning and Out-of-Distribution Detection
This addresses the need for robust model deployment in open-world scenarios, though it appears incremental by combining existing tasks.
The paper tackles the separate problems of active learning and out-of-distribution detection by introducing SISOM, a unified solution that achieves first place in two OpenOOD benchmarks and top-1 performance in three active learning benchmarks.
When applying deep learning models in open-world scenarios, active learning (AL) strategies are crucial for identifying label candidates from a nearly infinite amount of unlabeled data. In this context, robust out-of-distribution (OOD) detection mechanisms are essential for handling data outside the target distribution of the application. However, current works investigate both problems separately. In this work, we introduce SISOM as the first unified solution for both AL and OOD detection. By leveraging feature space distance metrics SISOM combines the strengths of the currently independent tasks to solve both effectively. We conduct extensive experiments showing the problems arising when migrating between both tasks. In these evaluations SISOM underlined its effectiveness by achieving first place in two of the widely used OpenOOD benchmarks and second place in the remaining one. In AL, SISOM outperforms others and delivers top-1 performance in three benchmarks