HiLRP: Toward One Trustworthy Explanation for Vision Transformer: Conservation-Valid Attribution via Attention Primitives
cs.CV, cs.AI
Submitted: 2026-09-01
Updated: 2026-09-28
Code: https://github.com/Nishan-Charlie/Hi-LRP-Towards-One-Trustworthy-Explainable-AI
Terminology
Sources
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- Separable Self-attention for Mobile Vision Transformers
- BEiT: BERT Pre-Training of Image Transformers
- Quantifying Attention Flow in Transformers
- AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers
- Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
- SmoothGrad: removing noise by adding noise
- RISE: Randomized Input Sampling for Explanation of Black-box Models
- Evaluating and Aggregating Feature-based Model Explanations
- A Consistent and Efficient Evaluation Strategy for Attribution Methods
- Precise Benchmarking of Explainable AI Attribution Methods
- ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features
- Captum: A unified and generic model interpretability library for PyTorch
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models