可解释性
变压器
计算机科学
人工智能
主管(地质)
计算机视觉
电气工程
工程类
地质学
电压
地貌学
作者
Sehyeong Jo,Gangjae Jang,Haesol Park
出处
期刊:Proceedings
[Institute of Electrical and Electronics Engineers]
日期:2025-08-18
卷期号:: 582-587
被引量:33
标识
DOI:10.1109/icip55913.2025.11084559
摘要
The Vision Transformer (ViT) has made significant advancements in computer vision, utilizing self-attention mechanisms to achieve state-of-the-art performance across various tasks, including image classification, object detection, and segmentation. Its architectural flexibility and capabilities have made it a preferred choice among researchers and practitioners. However, the intricate multi-head attention mechanism of ViT presents significant challenges to interpretability, as the underlying prediction process remains opaque. A critical limitation arises from an observation commonly noted in transformer architectures: "Not all attention heads are equally meaningful." Overlooking the relative importance of specific heads highlights the limitations of existing interpretability methods. To address these challenges, we introduce Gradient-Driven Multi-Head Attention Rollout (GMAR), a novel method that quantifies the importance of each attention head using gradient-based scores. These scores are normalized to derive a weighted aggregate attention score, effectively capturing the relative contributions of individual heads. GMAR clarifies the role of each head in the prediction process, enabling more precise interpretability at the head level. Experimental results demonstrate that GMAR consistently outperforms traditional attention rollout techniques. This work provides a practical contribution to transformer-based architectures, establishing a robust framework for enhancing the interpretability of Vision Transformer models.
科研通智能强力驱动
Strongly Powered by AbleSci AI