Convolutional Dynamic Alignment Networks for Interpretable Classifications
This addresses the need for interpretable AI models in domains requiring transparency, such as healthcare or finance, by offering a performant and inherently interpretable alternative to black-box neural networks.
The authors tackled the problem of creating interpretable neural networks by introducing Convolutional Dynamic Alignment Networks (CoDA-Nets), which achieve classification performance comparable to ResNet and VGG on datasets like CIFAR-10 and TinyImagenet while providing high-quality, model-inherent interpretability that outperforms existing attribution methods.
We introduce a new family of neural network models called Convolutional Dynamic Alignment Networks (CoDA-Nets), which are performant classifiers with a high degree of inherent interpretability. Their core building blocks are Dynamic Alignment Units (DAUs), which linearly transform their input with weight vectors that dynamically align with task-relevant patterns. As a result, CoDA-Nets model the classification prediction through a series of input-dependent linear transformations, allowing for linear decomposition of the output into individual input contributions. Given the alignment of the DAUs, the resulting contribution maps align with discriminative input patterns. These model-inherent decompositions are of high visual quality and outperform existing attribution methods under quantitative metrics. Further, CoDA-Nets constitute performant classifiers, achieving on par results to ResNet and VGG models on e.g. CIFAR-10 and TinyImagenet.