This Looks Like That: Deep Learning for Interpretable Image Recognition

From statwiki
Revision as of 19:55, 5 December 2020 by N2chatti (talk | contribs) (Previous Work)
Jump to: navigation, search

Presented by

Nouha Chatti


The motivation behind this paper is to introduce a new deep learning network architecture capable of reasoning in a humanly understandable way dealing with classification tasks. The idea is to perform these tasks by defining a form of interpretability when processing the images. The method suggested in this paper consists in dissecting parts of the input images and comparing them to prototypical parts of training images of a given class: Thus the expression this looks like that. In fact, this solution adds a transparency advantage to deep neural networks and allows the user to understand the actual process of decision making. It can intervene in many crucial problems that require understanding the actions that led to a particular output of the model. There are many fields that already rely on this case-based reasoning especially in the medical domain where diagnosis using X-ray scans is based on comparing these latter to other prototypical scans.

Previous Work

Interpretability in Deep neural networks has been a long-sought goal and seems to attract more and more attention recently. The opacity present in neural networks that leaves the user unaware of the exact process of how model makes predictions has inspired many studies where their ultimate goal was to reach a certain transparency. As a matter of fact, there already exists posthoc interpretability methods that analyze a performance of a trained CNN. Although this type of analysis do not explain the reasoning process of how a network actually makes its decisions during classification but are rather created after this phase. There are also attention-based models that determines parts of the input they are looking at but without associating them to prototypes.

Network Architecture

Figure 1 : Prototypical Part Network Architecture