Establishing baselines and introducing TernaryMixOE for fine-grained out-of-distribution detection
This work addresses the challenge of improving OOD detection for fine-grained classification, which is critical for deploying machine learning models in real-world scenarios where misclassification risks are high, though it appears incremental as it builds on existing OOD detection methods.
The paper tackles the problem of fine-grained out-of-distribution (OOD) detection, where models struggle to differentiate closely related classes, by introducing a theoretical framework, new baseline tasks, evaluation methods, and a loss function, but does not report specific performance numbers.
Machine learning models deployed in the open world may encounter observations that they were not trained to recognize, and they risk misclassifying such observations with high confidence. Therefore, it is essential that these models are able to ascertain what is in-distribution (ID) and out-of-distribution (OOD), to avoid this misclassification. In recent years, huge strides have been made in creating models that are robust to this distinction. As a result, the current state-of-the-art has reached near perfect performance on relatively coarse-grained OOD detection tasks, such as distinguishing horses from trucks, while struggling with finer-grained classification, like differentiating models of commercial aircraft. In this paper, we describe a new theoretical framework for understanding fine- and coarse-grained OOD detection, we re-conceptualize fine grained classification into a three part problem, and we propose a new baseline task for OOD models on two fine-grained hierarchical data sets, two new evaluation methods to differentiate fine- and coarse-grained OOD performance, along with a new loss function for models in this task.