Identifying Spurious Correlations and Correcting them with an Explanation-based Learning
Autor: | Hagos, Misgina Tsighe, Curran, Kathleen M., Mac Namee, Brian |
---|---|
Rok vydání: | 2022 |
Předmět: | |
Druh dokumentu: | Working Paper |
Popis: | Identifying spurious correlations learned by a trained model is at the core of refining a trained model and building a trustworthy model. We present a simple method to identify spurious correlations that have been learned by a model trained for image classification problems. We apply image-level perturbations and monitor changes in certainties of predictions made using the trained model. We demonstrate this approach using an image classification dataset that contains images with synthetically generated spurious regions and show that the trained model was overdependent on spurious regions. Moreover, we remove the learned spurious correlations with an explanation based learning approach. Comment: Presented at the NeurIPS 2022 workshop on Human-in-the-Loop Learning (HILL) |
Databáze: | arXiv |
Externí odkaz: |