explainable swin transformer 관련 자료 정리
<to do list>
understand how visualization of herbs works
success visualizaing attention map in vit
understand what do each feature maps in swin transformer stand for (and also in vit)
<reference>
Swin Transformer-Based Object Detection Model Using Explainable Meta-Learning Mining
In order to minimize damage in the event of a fire, the ignition point must be detected and dealt with before the fire spreads. However, the method of detecting fire by heat or fire is more damaging because it can be detected after the fire has spread. The
www.mdpi.com
>> 스윈트랜스포머 object detection
==>스윈 트랜스포머 explainable
Transformer Interpretability Beyond Attention Visualization (thecvf.com)
GitHub - hila-chefer/Transformer-Explainability: [CVPR 2021] Official PyTorch implementation for Transformer Interpretability Be
[CVPR 2021] Official PyTorch implementation for Transformer Interpretability Beyond Attention Visualization, a novel method to visualize classifications by Transformer based networks. - GitHub - hi...
github.com
==> explainability vit (paper + code)
[개념정리] LRP(Layer-wise Relevance Propagation) (velog.io)
Layer-wise Relevance Propagation - 공돌이의 수학정리노트 (Angelo's Math Notes) (angeloyeo.github.io)
Layer-wise Relevance Propagation - 공돌이의 수학정리노트 (Angelo's Math Notes)
angeloyeo.github.io
=> lrp
Vision Transformer (ViT) : Visualize Attention Map | Kaggle
Vision Transformer (ViT) : Visualize Attention Map
Explore and run machine learning code with Kaggle Notebooks | Using data from multiple data sources
www.kaggle.com
==>how to visualize attention map in vit