ProHOC: Probabilistic Hierarchical Out-of-Distribution Classification via Multi-Depth Networks
This addresses the limitation of traditional binary OOD detection by incorporating semantic relationships, which is incremental for improving classification in hierarchical domains.
The paper tackles the problem of out-of-distribution (OOD) detection by proposing a framework that classifies OOD samples into internal nodes of a class hierarchy, rather than treating them as binary OOD, and demonstrates effectiveness on three datasets with predefined hierarchies.
Out-of-distribution (OOD) detection in deep learning has traditionally been framed as a binary task, where samples are either classified as belonging to the known classes or marked as OOD, with little attention given to the semantic relationships between OOD samples and the in-distribution (ID) classes. We propose a framework for detecting and classifying OOD samples in a given class hierarchy. Specifically, we aim to predict OOD data to their correct internal nodes of the class hierarchy, whereas the known ID classes should be predicted as their corresponding leaf nodes. Our approach leverages the class hierarchy to create a probabilistic model and we implement this model by using networks trained for ID classification at multiple hierarchy depths. We conduct experiments on three datasets with predefined class hierarchies and show the effectiveness of our method. Our code is available at https://github.com/walline/prohoc.