all AI news
LeGrad: An Explainability Method for Vision Transformers via Feature Formation Sensitivity
April 5, 2024, 4:45 a.m. | Walid Bousselham, Angie Boggust, Sofian Chaybouti, Hendrik Strobelt, Hilde Kuehne
cs.CV updates on arXiv.org arxiv.org
Abstract: Vision Transformers (ViTs), with their ability to model long-range dependencies through self-attention mechanisms, have become a standard architecture in computer vision. However, the interpretability of these models remains a challenge. To address this, we propose LeGrad, an explainability method specifically designed for ViTs. LeGrad computes the gradient with respect to the attention maps of ViT layers, considering the gradient itself as the explainability signal. We aggregate the signal over all layers, combining the activations of …
arxiv cs.cv explainability feature sensitivity transformers type via vision vision transformers
More from arxiv.org / cs.CV updates on arXiv.org
Jobs in AI, ML, Big Data
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
AI Engineering Manager
@ M47 Labs | Barcelona, Catalunya [Cataluña], Spain