Abstract

A Formal concept lattice can be used to generate explanations from a black box model. This novel approach has been applied and proven for tabular data. It has also been compared to popular techniques in XAI. In this work, we apply the approach to image data. Image data, in general, comprises large dimensions and hence poses a challenge to build a formal concept lattice from such large data. We break the image into parts and build multiple sub-lattices. Using the combination of sub-lattice explanations, we generate the complete explanation for the entire image. We present our work beginning with a simple synthetic dataset for providing an intuitive idea of explanations and its credibility. This is followed by explanations of a model built on the popular MNIST dataset proving consistency of explanations on a real dataset. Text explanations from the lattice are converted to images for ease of visual understanding. We compare our work with DeepLIFT by viewing image masks obtained through contrastive explanation for specific digits from the MNIST dataset. This work proves the feasibility of using formal concept lattices for image data.