CVAIFeb 19, 2024

LangXAI: Integrating Large Vision Models for Generating Textual Explanations to Enhance Explainability in Visual Perception Tasks

arXiv:2402.12525v118 citationsh-index: 5IJCAI
Originality Incremental advance
AI Analysis

This addresses the explainability gap in AI for end-users with limited domain knowledge, though it is incremental as it builds on existing XAI and vision models.

The authors tackled the problem of making visual recognition tasks more understandable for non-expert users by developing LangXAI, a framework that generates textual explanations from model outputs, resulting in high BERTScore metrics across tasks.

LangXAI is a framework that integrates Explainable Artificial Intelligence (XAI) with advanced vision models to generate textual explanations for visual recognition tasks. Despite XAI advancements, an understanding gap persists for end-users with limited domain knowledge in artificial intelligence and computer vision. LangXAI addresses this by furnishing text-based explanations for classification, object detection, and semantic segmentation model outputs to end-users. Preliminary results demonstrate LangXAI's enhanced plausibility, with high BERTScore across tasks, fostering a more transparent and reliable AI framework on vision tasks for end-users.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes