Interventional Multi-Instance Learning with Deconfounded Instance-Level Prediction
Keywords:Computer Vision (CV), Reasoning Under Uncertainty (RU), Machine Learning (ML)
AbstractWhen applying multi-instance learning (MIL) to make predictions for bags of instances, the prediction accuracy of an instance often depends on not only the instance itself but also its context in the corresponding bag. From the viewpoint of causal inference, such bag contextual prior works as a confounder and may result in model robustness and interpretability issues. Focusing on this problem, we propose a novel interventional multi-instance learning (IMIL) framework to achieve deconfounded instance-level prediction. Unlike traditional likelihood-based strategies, we design an Expectation-Maximization (EM) algorithm based on causal intervention, providing a robust instance selection in the training phase and suppressing the bias caused by the bag contextual prior. Experiments on pathological image analysis demonstrate that our IMIL method substantially reduces false positives and outperforms state-of-the-art MIL methods.
How to Cite
Lin, T., Xu, H., Yang, C., & Xu, Y. (2022). Interventional Multi-Instance Learning with Deconfounded Instance-Level Prediction. Proceedings of the AAAI Conference on Artificial Intelligence, 36(2), 1601-1609. https://doi.org/10.1609/aaai.v36i2.20051
AAAI Technical Track on Computer Vision II