Graceful Degradation and Related Fields
This addresses the critical issue of model reliability in real-world deployed systems, particularly for visual applications, but it is incremental as it primarily provides a survey and conceptual framework.
The paper tackles the problem of machine learning models performing poorly on out-of-distribution data, such as over-confidence in errors, by defining and discussing graceful degradation to optimize model performance in such scenarios, and it surveys relevant areas by splitting the problem into active and passive approaches.
When machine learning models encounter data which is out of the distribution on which they were trained they have a tendency to behave poorly, most prominently over-confidence in erroneous predictions. Such behaviours will have disastrous effects on real-world machine learning systems. In this field graceful degradation refers to the optimisation of model performance as it encounters this out-of-distribution data. This work presents a definition and discussion of graceful degradation and where it can be applied in deployed visual systems. Following this a survey of relevant areas is undertaken, novelly splitting the graceful degradation problem into active and passive approaches. In passive approaches, graceful degradation is handled and achieved by the model in a self-contained manner, in active approaches the model is updated upon encountering epistemic uncertainties. This work communicates the importance of the problem and aims to prompt the development of machine learning strategies that are aware of graceful degradation.