Explainable Image Similarity: Integrating Siamese Networks and Grad-CAM
This addresses the need for interpretable image similarity in domains like image-based applications, though it appears incremental as it combines existing methods.
The paper tackles the problem of lack of transparency in image similarity models by proposing an explainable approach that integrates Siamese Networks and Grad-CAM to provide similarity scores with visual factual and counterfactual explanations, aiming to enhance interpretability and trust in real-world applications.
With the proliferation of image-based applications in various domains, the need for accurate and interpretable image similarity measures has become increasingly critical. Existing image similarity models often lack transparency, making it challenging to understand the reasons why two images are considered similar. In this paper, we propose the concept of explainable image similarity, where the goal is the development of an approach, which is capable of providing similarity scores along with visual factual and counterfactual explanations. Along this line, we present a new framework, which integrates Siamese Networks and Grad-CAM for providing explainable image similarity and discuss the potential benefits and challenges of adopting this approach. In addition, we provide a comprehensive discussion about factual and counterfactual explanations provided by the proposed framework for assisting decision making. The proposed approach has the potential to enhance the interpretability, trustworthiness and user acceptance of image-based systems in real-world image similarity applications. The implementation code can be found in https://github.com/ioannislivieris/Grad_CAM_Siamese.git.