Towards Visual Explainable Active Learning for Zero-Shot Classification

Zero-shot classification is a promising paradigm to solve an applicable problem when the training classes and test classes are disjoint. Achieving this usually needs experts to externalize their domain knowledge by manually specifying a class-attribute matrix to define which classes have which attri...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on visualization and computer graphics Vol. 28; no. 1; pp. 791 - 801
Main Authors: Jia, Shichao, Li, Zeyu, Chen, Nuo, Zhang, Jiawan
Format: Journal Article
Language:English
Published: United States IEEE 01.01.2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Active Learning
Classification
Explainable Artificial Intelligence
Human-AI Teaming
Labeling
Labels
Mixed-Initiative Visual Analytics
Navigation
Semantics
Task analysis
Testing
Training
Visual analytics
Zero-shot learning
ISSN:1077-2626, 1941-0506, 1941-0506
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Zero-shot classification is a promising paradigm to solve an applicable problem when the training classes and test classes are disjoint. Achieving this usually needs experts to externalize their domain knowledge by manually specifying a class-attribute matrix to define which classes have which attributes. Designing a suitable class-attribute matrix is the key to the subsequent procedure, but this design process is tedious and trial-and-error with no guidance. This paper proposes a visual explainable active learning approach with its design and implementation called semantic navigator to solve the above problems. This approach promotes human-AI teaming with four actions (ask, explain, recommend, respond) in each interaction loop. The machine asks contrastive questions to guide humans in the thinking process of attributes. A novel visualization called semantic map explains the current status of the machine. Therefore analysts can better understand why the machine misclassifies objects. Moreover, the machine recommends the labels of classes for each attribute to ease the labeling burden. Finally, humans can steer the model by modifying the labels interactively, and the machine adjusts its recommendations. The visual explainable active learning approach improves humans' efficiency of building zero-shot classification models interactively, compared with the method without guidance. We justify our results with user studies using the standard benchmarks for zero-shot classification.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1077-2626
1941-0506
1941-0506
DOI:10.1109/TVCG.2021.3114793