Long-Tailed Out-of-Distribution Detection with Refined Separate Class Learning
This work addresses a critical robustness issue for deploying machine learning models in real-world scenarios with imbalanced data, representing an incremental improvement over existing separate class learning methods.
The paper tackles the problem of out-of-distribution (OOD) detection in long-tailed data distributions, where confusion between OOD samples and head/tail classes reduces accuracy, and proposes Refined Separate Class Learning (RSCL) with dynamic temperature adjustment and outlier mining, achieving superior OOD detection performance and improved in-distribution classification accuracy in experiments.
Out-of-distribution (OOD) detection is crucial for deploying robust machine learning models. However, when training data follows a long-tailed distribution, the model's ability to accurately detect OOD samples is significantly compromised, due to the confusion between OOD samples and head/tail classes. To distinguish OOD samples from both head and tail classes, the separate class learning (SCL) approach has emerged as a promising solution, which separately conduct head-specific and tail-specific class learning. To this end, we examine the limitations of existing works of SCL and reveal that the OOD detection performance is notably influenced by the use of static scaling temperature value and the presence of uninformative outliers. To mitigate these limitations, we propose a novel approach termed Refined Separate Class Learning (RSCL), which leverages dynamic class-wise temperature adjustment to modulate the temperature parameter for each in-distribution class and informative outlier mining to identify diverse types of outliers based on their affinity with head and tail classes. Extensive experiments demonstrate that RSCL achieves superior OOD detection performance while improving the classification accuracy on in-distribution data.