DeepAI AI Chat
Log In Sign Up

Visual correspondence-based explanations improve AI robustness and human-AI team accuracy

07/26/2022
by   Giang Nguyen, et al.
14

Explaining artificial intelligence (AI) predictions is increasingly important and even imperative in many high-stakes applications where humans are the ultimate decision-makers. In this work, we propose two novel architectures of self-interpretable image classifiers that first explain, and then predict (as opposed to post-hoc explanations) by harnessing the visual correspondences between a query image and exemplars. Our models consistently improve (by 1 to 4 points) on out-of-distribution (OOD) datasets while performing marginally worse (by 1 to 2 points) on in-distribution tests than ResNet-50 and a k-nearest neighbor classifier (kNN). Via a large-scale, human study on ImageNet and CUB, our correspondence-based explanations are found to be more useful to users than kNN explanations. Our explanations help users more accurately reject AI's wrong decisions than all other tested methods. Interestingly, for the first time, we show that it is possible to achieve complementary human-AI team accuracy (i.e., that is higher than either AI-alone or human-alone), in ImageNet and CUB image classification tasks.

READ FULL TEXT

page 4

page 10

page 11

page 12

page 13

page 14

page 15

page 18

06/26/2020

Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance

Increasingly, organizations are pairing humans with AI systems to improv...
11/22/2022

Towards Human-Interpretable Prototypes for Visual Assessment of Image Classification Models

Explaining black-box Artificial Intelligence (AI) models is a cornerston...
10/11/2022

On Explainability in AI-Solutions: A Cross-Domain Survey

Artificial Intelligence (AI) increasingly shows its potential to outperf...
11/30/2022

Optimizing Explanations by Network Canonization and Hyperparameter Search

Explainable AI (XAI) is slowly becoming a key component for many AI appl...
05/31/2021

The effectiveness of feature attribution methods and its correlation with automatic evaluation scores

Explaining the decisions of an Artificial Intelligence (AI) model is inc...
07/23/2020

Are Visual Explanations Useful? A Case Study in Model-in-the-Loop Prediction

We present a randomized controlled trial for a model-in-the-loop regress...