Incremental Generalized Category Discovery
This addresses a challenging incremental learning problem for fine-grained visual categorization, but it is incremental as it builds on existing category discovery and incremental learning approaches.
The paper tackles the problem of Incremental Generalized Category Discovery (IGCD), where models must categorize images from seen categories and discover novel ones over time, using a new method that combines non-parametric categorization with efficient image sampling to mitigate catastrophic forgetting, achieving superior performance over existing methods on the proposed iNatIGCD benchmark dataset.
We explore the problem of Incremental Generalized Category Discovery (IGCD). This is a challenging category incremental learning setting where the goal is to develop models that can correctly categorize images from previously seen categories, in addition to discovering novel ones. Learning is performed over a series of time steps where the model obtains new labeled and unlabeled data, and discards old data, at each iteration. The difficulty of the problem is compounded in our generalized setting as the unlabeled data can contain images from categories that may or may not have been observed before. We present a new method for IGCD which combines non-parametric categorization with efficient image sampling to mitigate catastrophic forgetting. To quantify performance, we propose a new benchmark dataset named iNatIGCD that is motivated by a real-world fine-grained visual categorization task. In our experiments we outperform existing related methods