Assisting human experts in the interpretation of their visual process: A case study on assessing copper surface adhesive potency

TL;DR

This paper presents a deep learning model that aids human experts in interpreting microscopic images of copper surfaces to assess adhesive potency, bridging the gap between AI interpretability and human reasoning.

Contribution

The study introduces a model that provides visual explanations to help experts justify their recognition decisions on copper surface images.

Findings

Model successfully provides visual cues for expert interpretation.

Assists in testing hypotheses about manufacturing process effects.

Enhances understanding of surface characteristics through AI explanations.

Abstract

Deep Neural Networks are often though to lack interpretability due to the distributed nature of their internal representations. In contrast, humans can generally justify, in natural language, for their answer to a visual question with simple common sense reasoning. However, human introspection abilities have their own limits as one often struggles to justify for the recognition process behind our lowest level feature recognition ability: for instance, it is difficult to precisely explain why a given texture seems more characteristic of the surface of a finger nail rather than a plastic bottle. In this paper, we showcase an application in which deep learning models can actually help human experts justify for their own low-level visual recognition process: We study the problem of assessing the adhesive potency of copper sheets from microscopic pictures of their surface. Although highly trained material experts are able to qualitatively assess the surface adhesive potency, they are often unable to precisely justify for their decision process. We present a model that, under careful design considerations, is able to provide visual clues for human experts to understand and justify for their own recognition process. Not only can our model assist human experts in their interpretation of the surface characteristics, we show how this model can be used to test different hypothesis of the copper surface response to different manufacturing processes.