Neural Additive Image Model: Interpretation through Interpolation
This addresses the challenge of interpreting image-based predictions for applications like pricing analysis, though it appears to be an incremental extension of existing interpretability methods to image data.
The paper tackles the problem of interpreting how image characteristics influence outcomes by proposing a Neural Additive Image Model that combines Neural Additive Models with Diffusion Autoencoders to identify latent image semantics and achieve intelligibility of tabular effects. They demonstrate the method's ability to precisely identify complex image effects in an ablation study and apply it to investigate how Airbnb host image features affect rental pricing.
Understanding how images influence the world, interpreting which effects their semantics have on various quantities and exploring the reasons behind changes in image-based predictions are highly difficult yet extremely interesting problems. By adopting a holistic modeling approach utilizing Neural Additive Models in combination with Diffusion Autoencoders, we can effectively identify the latent hidden semantics of image effects and achieve full intelligibility of additional tabular effects. Our approach offers a high degree of flexibility, empowering us to comprehensively explore the impact of various image characteristics. We demonstrate that the proposed method can precisely identify complex image effects in an ablation study. To further showcase the practical applicability of our proposed model, we conduct a case study in which we investigate how the distinctive features and attributes captured within host images exert influence on the pricing of Airbnb rentals.