A multimodal explanation-guided learning framework that jointly uses visual saliency maps and textual rationales to train image classifiers, improving accuracy, visual explanation overlap, and text explanation scores on two new datasets.
A survey on xai and nat- ural language explanations
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MEGL: Multimodal Explanation-Guided Learning
A multimodal explanation-guided learning framework that jointly uses visual saliency maps and textual rationales to train image classifiers, improving accuracy, visual explanation overlap, and text explanation scores on two new datasets.