Interpretable Image Recognition with Hierarchical Prototypes

By Peter Hase, Oscar Li, Cynthia Rudin. 2019

138 citations recorded by the source corpus.

Vision models are interpretable when they classify objects on the basis of features that a person can directly understand. Recently, methods relying on visual feature prototypes have been developed for this purpose. However, in contrast to how humans categorize objects, these approaches have not yet made use of any taxonomical organization of class labels. With such an approach, for instance, we may see why a chimpanzee is classified as a chimpanzee, but not why it was considered to be a primate or even an animal. In this work we introduce a model that uses hierarchically organized prototypes to classify objects at every level in a predefined taxonomy. Hence, we may find distinct explanations for the prediction an image receives at each level of the taxonomy. The hierarchical prototypes enable the model to perform another important task: interpretably classifying images from previously unseen classes at the level of the taxonomy to which they correctly relate, e.g. classifying a hand gun as a weapon, when the only weapons in the training data are rifles. With a subset of ImageNet, we test our model against its counterpart black-box model on two tasks: 1) classification of data from familiar classes, and 2) classification of data from previously unseen classes at the appropriate level in the taxonomy. We find that our model performs approximately as well as its counterpart black-box model while allowing for each classification to be interpreted.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Neural Prototype Trees for Interpretable Fine-grained Image Recognition (2020, background): “, a gibbon is an animal and a primate) such as [20], since we do not require hierarchical labels or a predefined taxonomy.”
XProtoNet: Diagnosis in Chest Radiography with Global and Local Explanations (2021, unknown): “Case-based models learn discriminative features of each class, which are referred to as prototypes, and classify an input image by comparing its features with the prototypes [3, 8, 16].”
AUC Maximization in the Era of Big Data and AI: A Survey (2022, background): “Two issues are of foremost importance, namely fairness [7, 10, 20, 113] and interpretability [3, 24, 64].”
Evaluating Explainable AI: Which Algorithmic Explanations Help Users Predict Model Behavior? (2020, methodology): “Two works on prototype models for computer vision introduced neural models that learn prototypes corresponding to parts of images (Chen et al., 2019; Hase et al., 2019).”
Decoupling Deep Learning for Interpretable Image Recognition (2022, methodology): “We represent feature maps by matrix: Previous prototyped-based models [3, 26, 25, 13, 9, 17] can be divided into three types of prototype extraction methods represented by ProtoPNet [3], Gen-ProtoPNet [25], and XProtoNet [13].”