Out-of-Distribution Detection: A Task-Oriented Survey of Recent Advances
It addresses the need for a structured review to guide researchers and practitioners in developing reliable machine learning systems, but it is incremental as it builds on existing surveys by adding a new perspective.
This survey tackles the problem of organizing recent advances in out-of-distribution (OOD) detection by introducing a task-oriented taxonomy based on user access to models, categorizing methods as training-driven, training-agnostic, or large pre-trained model-based, and it provides a curated resource for future research.
Out-of-distribution (OOD) detection aims to detect test samples outside the training category space, which is an essential component in building reliable machine learning systems. Existing reviews on OOD detection primarily focus on method taxonomy, surveying the field by categorizing various approaches. However, many recent works concentrate on non-traditional OOD detection scenarios, such as test-time adaptation, multi-modal data sources and other novel contexts. In this survey, we uniquely review recent advances in OOD detection from the task-oriented perspective for the first time. According to the user's access to the model, that is, whether the OOD detection method is allowed to modify or retrain the model, we classify the methods as training-driven or training-agnostic. Besides, considering the rapid development of pre-trained models, large pre-trained model-based OOD detection is also regarded as an important category and discussed separately. Furthermore, we provide a discussion of the evaluation scenarios, a variety of applications, and several future research directions. We believe this survey with new taxonomy will benefit the proposal of new methods and the expansion of more practical scenarios. A curated list of related papers is provided in the Github repository: https://github.com/shuolucs/Awesome-Out-Of-Distribution-Detection.