Saved in:
Bibliographic Details
Main Authors: Nguyen, Hoang C., Lee, Haeil, Kim, Junmo
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2311.11378
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915250281906176
author Nguyen, Hoang C.
Lee, Haeil
Kim, Junmo
author_facet Nguyen, Hoang C.
Lee, Haeil
Kim, Junmo
contents Transformer becomes more popular in the vision domain in recent years so there is a need for finding an effective way to interpret the Transformer model by visualizing it. In recent work, Chefer et al. can visualize the Transformer on vision and multi-modal tasks effectively by combining attention layers to show the importance of each image patch. However, when applying to other variants of Transformer such as the Swin Transformer, this method can not focus on the predicted object. Our method, by considering the statistics of tokens in layer normalization layers, shows a great ability to interpret the explainability of Swin Transformer and ViT.
format Preprint
id arxiv_https___arxiv_org_abs_2311_11378
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Inspecting Explainability of Transformer Models with Additional Statistical Information
Nguyen, Hoang C.
Lee, Haeil
Kim, Junmo
Computer Vision and Pattern Recognition
Artificial Intelligence
Transformer becomes more popular in the vision domain in recent years so there is a need for finding an effective way to interpret the Transformer model by visualizing it. In recent work, Chefer et al. can visualize the Transformer on vision and multi-modal tasks effectively by combining attention layers to show the importance of each image patch. However, when applying to other variants of Transformer such as the Swin Transformer, this method can not focus on the predicted object. Our method, by considering the statistics of tokens in layer normalization layers, shows a great ability to interpret the explainability of Swin Transformer and ViT.
title Inspecting Explainability of Transformer Models with Additional Statistical Information
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2311.11378