• Home
  • Search
  • Human-AI Interactive and Continuous Sensemaking: A Case Study of Image Classification using Scribble Attention Maps
  • Cite Icon21
  • https://doi.org/10.1145/3411763.3451798Copy DOI Icon

Human-AI Interactive and Continuous Sensemaking: A Case Study of Image Classification using Scribble Attention Maps

  • May 8, 2021
  • Haifeng Shen +6 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Advances in Artificial Intelligence (AI), especially the stunning achievements of Deep Learning (DL) in recent years, have shown AI/DL models possess remarkable understanding towards the logic reasoning behind the solved tasks. However, human understanding towards what knowledge is captured by deep neural networks is still elementary and this has a detrimental effect on human’s trust in the decisions made by AI systems. Explainable AI (XAI) is a hot topic in both AI and HCI communities in order to open up the blackbox to elucidate the reasoning processes of AI algorithms in such a way that makes sense to humans. However, XAI is only half of human-AI interaction and research on the other half - human’s feedback on AI explanations together with AI making sense of the feedback - is generally lacking. Human cognition is also a blackbox to AI and effective human-AI interaction requires unveiling both blackboxes to each other for mutual sensemaking. The main contribution of this paper is a conceptual framework for supporting effective human-AI interaction, referred to as interactive and continuous sensemaking (HAICS). We further implement this framework in an image classification application using deep Convolutional Neural Network (CNN) classifiers as a browser-based tool that displays network attention maps to the human for explainability and collects human’s feedback in the form of scribble annotations overlaid onto the maps. Experimental results using a real-world dataset has shown significant improvement of classification accuracy (the AI performance) with the HAICS framework.

Similar Papers
  • Research Article
  • Citations51

Predictive modeling in reproductive medicine: Where will the future of artificial intelligence research take us?

  • Nov 01, 2020
  • Fertility and Sterility
  • Carol Lynn Curchoe +18
  • Research Article
  • Citations4

Human-Computer Interaction Techniques for Explainable Artificial Intelligence Systems

  • Mar 26, 2024
  • Research & Review: Machine Learning and Cloud Computing
  • S Tharun Anand Reddy
  • Discussion
  • Citations8

Focus issue: Artificial intelligence in medical physics.

  • Mar 01, 2021
  • Physica Medica
  • F Zanca +11
  • Research Article

(DCNN) Deep Convolution Neural Network Classifier and (EW-CSA) Earth Worm-Crow Search Algorithm for Lane Detection

  • Nov 10, 2019
  • International Journal of Innovative Technology and Exploring Engineering
  • Suvarna Shirke +2
  • Research Article
  • Citations62

ChatGPT Isn't Magic

  • Oct 02, 2023
  • M/C Journal
  • Tama Leaver +1
  • Research Article
  • Citations3

Detecting Coronary Artery Calcium on Chest Radiographs: Can We Teach an Old Dog New Tricks?

  • Jun 01, 2021
  • Radiology. Cardiothoracic imaging
  • Sumit Gupta +1
  • Research Article
  • Citations13

Handwritten Kannada numerals recognition using deep learning convolution neural network (DCNN) classifier

  • May 11, 2020
  • CSI Transactions on ICT
  • Vishweshwrayya C Hallur +1
  • Research Article
  • Citations14

Artificial intelligence: Friend or foe?

  • Apr 01, 2023
  • Australian and New Zealand Journal of Obstetrics and Gynaecology
  • Anusch Yazdani +2
  • PDF
  • Research Article
  • Citations147

Who Gets Credit for AI-Generated Art?

  • Aug 29, 2020
  • iScience
  • Ziv Epstein +3
  • Research Article
  • Citations20

Artificial intelligence in interdisciplinary life science and drug discovery research.

  • Mar 08, 2022
  • Future science OA
  • Jürgen Bajorath
  • Research Article
  • Citations44

Explainable AI: The Effect of Contradictory Decisions and Explanations on Users’ Acceptance of AI Systems

  • Oct 13, 2022
  • International Journal of Human–Computer Interaction
  • Carolin Ebermann +2
  • Research Article
  • Citations82

Growing random forest on deep convolutional neural networks for scene categorization

  • Oct 17, 2016
  • Expert Systems with Applications
  • Shuang Bai
  • Research Article
  • Citations26

A robust pathological voices recognition system based on DCNN and scattering transform

  • Mar 03, 2021
  • Applied Acoustics
  • Sameh Souli +2
  • PDF
  • Research Article
  • Citations14

Towards Robustifying Image Classifiers against the Perils of Adversarial Attacks on Artificial Intelligence Systems

  • Sep 13, 2022
  • Sensors (Basel, Switzerland)
  • Theodora Anastasiou +6
  • PDF
  • Research Article
  • Citations7

Comprehensive Study for Breast Cancer Using Deep Learning and Traditional Machine Learning

  • Apr 12, 2022
  • ZANCO JOURNAL OF PURE AND APPLIED SCIENCES
  • Chiman Haydar Salh +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.