PICNN: A Pathway towards Interpretable Convolutional Neural Networks
DOI:
https://doi.org/10.1609/aaai.v38i3.27971Keywords:
CV: Interpretability, Explainability, and TransparencyAbstract
Convolutional Neural Networks (CNNs) have exhibited great performance in discriminative feature learning for complex visual tasks. Besides discrimination power, interpretability is another important yet under-explored property for CNNs. One difficulty in the CNN interpretability is that filters and image classes are entangled. In this paper, we introduce a novel pathway to alleviate the entanglement between filters and image classes. The proposed pathway groups the filters in a late conv-layer of CNN into class-specific clusters. Clusters and classes are in a one-to-one relationship. Specifically, we use the Bernoulli sampling to generate the filter-cluster assignment matrix from a learnable filter-class correspondence matrix. To enable end-to-end optimization, we develop a novel reparameterization trick for handling the non-differentiable Bernoulli sampling. We evaluate the effectiveness of our method on ten widely used network architectures (including nine CNNs and a ViT) and five benchmark datasets. Experimental results have demonstrated that our method PICNN (the combination of standard CNNs with our proposed pathway) exhibits greater interpretability than standard CNNs while achieving higher or comparable discrimination power.Downloads
Published
2024-03-24
How to Cite
Guo, W., Yang, J., Yin, H., Chen, Q., & Ye, W. (2024). PICNN: A Pathway towards Interpretable Convolutional Neural Networks. Proceedings of the AAAI Conference on Artificial Intelligence, 38(3), 2003-2012. https://doi.org/10.1609/aaai.v38i3.27971
Issue
Section
AAAI Technical Track on Computer Vision II