Explainable Interactive Projections for Image Data

Han, Huimin; Faust, Rebecca; Norambuena, Brian Felipe Keith; Prabhu, Ritvik; Smith, Timothy; Li, Song; North, Chris; Bebis, G; Li, B; Yao, A; Liu, Y; Duan, Y; Lau, M; Khadka, R; Crisan, A; et. al.

Abstract

Making sense of large collections of images is difficult. Dimension reductions (DR) assist by organizing images in a 2D space based on similarities, but provide little support for explaining why images were placed together or apart in the 2D space. Additionally, they do not provide support for modifying and updating the 2D space to explore new relationships and organizations of images. To address these problems, we present an interactive DR method for images that uses visual features extracted by a deep neural network to project the images into 2D space and provides visual explanations of image features that contributed to the 2D location. In addition, it allows people to directly manipulate the 2D projection space to define alternative relationships and explore subsequent projections of the images. With an iterative cycle of semantic interaction and explainable-AI feedback, people can explore complex visual relationships in image data. Our approach to human-AI interaction integrates visual knowledge from both human mental models and pre-trained deep neural models to explore image data. We demonstrate our method through examples with collaborators in agricultural science.

Más información

Título según WOS: ID WOS:000916102000006 Not found in local WOS DB
Título de la Revista: BIO-INSPIRED SYSTEMS AND APPLICATIONS: FROM ROBOTICS TO AMBIENT INTELLIGENCE, PT II
Volumen: 13598
Editorial: SPRINGER INTERNATIONAL PUBLISHING AG
Fecha de publicación: 2022
Página de inicio: 77
Página final: 90
DOI:

10.1007/978-3-031-20713-6_6

Notas: ISI