A Unified Approach Towards Active Learning and Out-of-Distribution Detection

TMLR Paper4629 Authors

Abstract:

In real-world applications of deep learning models, active learning (AL) strategies are essential for identifying label candidates from vast amounts of unlabeled data. In this context, robust out-of-distribution (OOD) detection mechanisms are crucial for handling data out-
side the target distribution during the application’s operation. Usually, these problems have been addressed separately. In this work, we introduce SISOM as a unified solution designed explicitly for AL and OOD detection. By combining feature space-based and uncertainty-
based metrics, SISOM leverages the strengths of the currently independent tasks to solve both effectively, without requiring specific training schemes. We conducted extensive experiments showing the problems arising when migrating between both tasks. In our experiments
SISOM underlined its effectiveness by achieving first place in two of the commonly used OpenOOD benchmarks settings and second place in the remaining one for near-OOD data. In AL, SISOM outperforms others and delivers top-1 performance in three benchmarks.

Submission Length: Regular submission (no more than 12 pages of main content)

Assigned Action Editor: ~Chicheng_Zhang1

Submission Number: 4629