Incremental Fast Subclass Discriminant Analysis
This is an incremental improvement for researchers and practitioners in machine learning, specifically in image analysis, by enabling faster updates to discriminant analysis models.
The paper tackled the problem of making Fast Subclass Discriminant Analysis (fastSDA) incremental, proposing exact and approximate linear solutions and a kernelized variant, with experiments on eight image datasets showing training time improvements while maintaining accuracy close to fastSDA and outperforming other methods.
This paper proposes an incremental solution to Fast Subclass Discriminant Analysis (fastSDA). We present an exact and an approximate linear solution, along with an approximate kernelized variant. Extensive experiments on eight image datasets with different incremental batch sizes show the superiority of the proposed approach in terms of training time and accuracy being equal or close to fastSDA solution and outperforming other methods.