Attention-Based Prototypical Learning Towards Interpretable, Confident and Robust Deep Neural Networks

By Sercan Ö. Arik, Tomas Pfister. 2019

19 citations recorded by the source corpus.

We propose a new framework for prototypical learning that bases decision-making on few relevant examples that we call prototypes. Our framework utilizes an attention mechanism that relates the encoded representations to determine the prototypes. This results in a model that: (1) enables interpretability by outputting samples most relevant to the decision-making in addition to outputting the classification results; (2) allows confidence-controlled prediction by quantifying the mismatch across prototype labels; (3) permits detection of distribution mismatch; and (4) improves robustness to label noise. We demonstrate that our model is able to maintain comparable performance to baseline models while enabling all these benefits.

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

A Survey on Explainable Artificial Intelligence (XAI): Toward Medical XAI (2019, methodology): “ProtoAttend [104] uses probabilities as weights in the linear component of the”
This Looks Like That, Because ... Explaining Prototypes for Interpretable Image Recognition (2020, background): “, images from the training set that look similar to the image being classified [2, 6, 27, 32].”
Attribute Prototype Network for Zero-Shot Learning (2020, methodology): “Prototype learning is considered to be more robust when handling open-set recognition [46, 32], out-of-distribution samples [3] and few-shot learning [33, 11, 28].”
On Concept-Based Explanations in Deep Neural Networks (2019, background): “Most works fall under two categories: (i) feature-based explanation methods, that attribute the decision to important input features [23, 19, 26, 6], and (ii) sample-based explanation methods, that attribute the decision to previously observed samples [17, 30, 13, 2].”
On Completeness-aware Concept-Based Explanations in Deep Neural Networks (2019, background): “…input features [1, 2, 13, 14], (b) sample-based explanation methods, that attribute the decision to previously observed samples [15, 16, 17, 18], and (c) counterfactual-based explanation methods, which answers the question: “what to alter in the current input to change the outcome of the…”