Header

UZH-Logo

Maintenance Infos

Bridging Trustworthiness and Open-World Learning: An Exploratory Neural Approach for Enhancing Interpretability, Generalization, and Robustness


Du, Shide; Fang, Zihan; Lan, Shiyang; Tan, Yanchao; Günther, Manuel; Wang, Shiping; Guo, Wenzhong (2023). Bridging Trustworthiness and Open-World Learning: An Exploratory Neural Approach for Enhancing Interpretability, Generalization, and Robustness. In: MM '23: The 31st ACM International Conference on Multimedia, Ottawa ON Canada, 29 October 2023 - 3 November 2023. ACM Digital library, 8719-8729.

Abstract

As researchers strive to narrow the gap between machine intelligence and human through the development of artificial intelligence multimedia technologies, it is imperative that we recognize the critical importance of trustworthiness in open-world, which has become ubiquitous in all aspects of daily life for everyone. However, several challenges may create a crisis of trust in current open-world artificial multimedia systems that need to be bridged: 1) Insufficient explanation of predictive results; 2) Inadequate generalization for learning models; 3) Poor adaptability to uncertain environments. Consequently, we explore a neural program to bridge trustworthiness and open-world learning, extending from single-modal to multi-modal scenarios for readers.1) To enhance design-level interpretability, we first customize trustworthy networks with specific physical meanings; 2) We then design environmental well-being task-interfaces via flexible learning regularizers for improving the generalization of trustworthy learning; 3) We propose to increase the robustness of trustworthy learning by integrating open-world recognition losses with agent mechanisms. Eventually, we enhance various trustworthy properties through the establishment of design-level explainability, environmental well-being task-interfaces and open-world recognition programs. As a result, these designed open-world protocols are applicable across a wide range of surroundings, under open-world multimedia recognition scenarios with significant performance improvements observed.

Abstract

As researchers strive to narrow the gap between machine intelligence and human through the development of artificial intelligence multimedia technologies, it is imperative that we recognize the critical importance of trustworthiness in open-world, which has become ubiquitous in all aspects of daily life for everyone. However, several challenges may create a crisis of trust in current open-world artificial multimedia systems that need to be bridged: 1) Insufficient explanation of predictive results; 2) Inadequate generalization for learning models; 3) Poor adaptability to uncertain environments. Consequently, we explore a neural program to bridge trustworthiness and open-world learning, extending from single-modal to multi-modal scenarios for readers.1) To enhance design-level interpretability, we first customize trustworthy networks with specific physical meanings; 2) We then design environmental well-being task-interfaces via flexible learning regularizers for improving the generalization of trustworthy learning; 3) We propose to increase the robustness of trustworthy learning by integrating open-world recognition losses with agent mechanisms. Eventually, we enhance various trustworthy properties through the establishment of design-level explainability, environmental well-being task-interfaces and open-world recognition programs. As a result, these designed open-world protocols are applicable across a wide range of surroundings, under open-world multimedia recognition scenarios with significant performance improvements observed.

Statistics

Citations

Dimensions.ai Metrics

Altmetrics

Downloads

7 downloads since deposited on 09 Feb 2024
7 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Conference or Workshop Item (Paper), not_refereed, original work
Communities & Collections:03 Faculty of Economics > Department of Informatics
08 Research Priority Programs > Digital Society Initiative
Dewey Decimal Classification:000 Computer science, knowledge & systems
Scopus Subject Areas:Physical Sciences > Artificial Intelligence
Physical Sciences > Computer Graphics and Computer-Aided Design
Physical Sciences > Human-Computer Interaction
Physical Sciences > Software
Scope:Discipline-based scholarship (basic research)
Language:English
Event End Date:3 November 2023
Deposited On:09 Feb 2024 10:08
Last Modified:25 Mar 2024 08:35
Publisher:ACM Digital library
Series Name:Proceedings of the ACM International Conference on Multimedia Retrieval
ISBN:979-8-4007-0108-5
OA Status:Green
Publisher DOI:https://doi.org/10.1145/3581783.3612352
Other Identification Number:merlin-id:24399
  • Content: Accepted Version
  • Language: English
  • Licence: Creative Commons: Attribution 4.0 International (CC BY 4.0)