Empirical Evidences for the Effects of Feature Diversity in Open Set Recognition and Continual Learning
This work addresses incremental improvements in open set recognition and continual learning for machine learning systems.
The study investigated the impact of feature diversity on open set recognition and continual learning, finding that increased diversity improves detection of novel classes and aids in retaining old knowledge while integrating new data.
Open set recognition (OSR) and continual learning are two critical challenges in machine learning, focusing respectively on detecting novel classes at inference time and updating models to incorporate the new classes. While many recent approaches have addressed these problems, particularly OSR, by heuristically promoting feature diversity, few studies have directly examined the role that feature diversity plays in tackling them. In this work, we provide empirical evidence that enhancing feature diversity improves the recognition of open set samples. Moreover, increased feature diversity also facilitates both the retention of previously learned data and the integration of new data in continual learning. We hope our findings can inspire further research into both practical methods and theoretical understanding in these domains.