Embedded Encoder-Decoder in Convolutional Networks Towards Explainable AI
arXiv:2007.06712
Abstract
Understanding intermediate layers of a deep learning model and discovering the driving features of stimuli have attracted much interest, recently. Explainable artificial intelligence (XAI) provides a new way to open an AI black box and makes a transparent and interpretable decision. This paper proposes a new explainable convolutional neural network (XCNN) which represents important and driving visual features of stimuli in an end-to-end model architecture. This network employs encoder-decoder neural networks in a CNN architecture to represent regions of interest in an image based on its category. The proposed model is trained without localization labels and generates a heat-map as part of the network architecture without extra post-processing steps. The experimental results on the CIFAR-10, Tiny ImageNet, and MNIST datasets showed the success of our algorithm (XCNN) to make CNNs explainable. Based on visual assessment, the proposed model outperforms the current algorithms in class-specific feature representation and interpretable heatmap generation while providing a simple and flexible network architecture. The initial success of this approach warrants further study to enhance weakly supervised localization and semantic segmentation in explainable frameworks.
References in corpus (7)
- Methods for Interpreting and Understanding Deep Neural Networks
- Striving for Simplicity: The All Convolutional Net
- Explaining NonLinear Classification Decisions with Deep Taylor Decomposition
- NIPS 2016 Tutorial: Generative Adversarial Networks
- Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learning
- How convolutional neural network see the world - A survey of convolutional neural network visualization methods
- TreeView: Peeking into Deep Neural Networks Via Feature-Space Partitioning