Exploring specialization and sensitivity of convolutional neural networks in the context of simultaneous image augmentations
This work provides a method for explainable AI research that could potentially be transferred to studying biological neural networks, though it appears incremental in adapting existing paradigms to this specific context.
The authors tackled the problem of understanding how convolutional neural networks respond to simultaneous image augmentations by developing a framework that measures activation changes using variance decomposition with Sobol indices and Shapley values, enabling visualization of sensitivity and guided masking of activations.
Drawing parallels with the way biological networks are studied, we adapt the treatment--control paradigm to explainable artificial intelligence research and enrich it through multi-parametric input alterations. In this study, we propose a framework for investigating the internal inference impacted by input data augmentations. The internal changes in network operation are reflected in activation changes measured by variance, which can be decomposed into components related to each augmentation, employing Sobol indices and Shapley values. These quantities enable one to visualize sensitivity to different variables and use them for guided masking of activations. In addition, we introduce a way of single-class sensitivity analysis where the candidates are filtered according to their matching to prediction bias generated by targeted damaging of the activations. Relying on the observed parallels, we assume that the developed framework can potentially be transferred to studying biological neural networks in complex environments.