Improving the Performance of Already Trained Classifiers Through an Automatic Explanation-Based Learning Approach

While much of the existing XAI literature focuses on explaining AI systems, there has recently been a growing interest in using XAI techniques to improve the performance of AI systems without human involvement. In this context, we propose a novel explanation-based learning approach that aims to improve the performance of an already trained Deep-Learning (DL) classifier M without the need for extensive retraining. Our approach involves augmenting the responses of M with specific and relevant features obtained from a predictor P of explanations, which is trained to highlight relevant information in terms of input encoded features. These encoded features, together with the responses provided by M, are then fed into an additional simple classifier to produce a new classification. Importantly, P is constructed so that its training is less computationally expensive than training M from scratch, or equivalent to fine-tuning M. This approach avoids the computational cost associated with training a complex DL model from scratch. To evaluate our proposal, we used 1) three different well-known DL models as M, specifically EfficientNet-B2, MobileNet, LeNet-5, and 2) three standard image datasets, specifically CIFAR-10, CIFAR-100 and STL-10. The results show that our approach uniformly improves the performance of all already trained DL models for all the inspected datasets.