Bridging Human and Model Attention: Explainability Analysis of CNN, Mamba, and ViT Architectures with Gaze-Based Validation
cs.CV, cs.HC, cs.LG
Submitted: 2026-10-08
Updated: 2026-10-08
Comments: Submitted to Image and Vision Computing
Code: https://github.com/zhangyongshun/resnet_
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- What do we need to build explainable AI systems for the medical domain?
- Explainable deep learning models in medical image analysis
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- DriverGaze360: OmniDirectional Driver Attention with Object-Level Guidance
- Towards better understanding of gradient-based attribution methods for Deep Neural Networks
- Sampling Permutations for Shapley Value Estimation
- Striving for Simplicity: The All Convolutional Net
- Explaining NonLinear Classification Decisions with Deep Taylor Decomposition
- Learning Important Features Through Propagating Activation Differences
- A Unified Approach to Interpreting Model Predictions
- Quantifying Attention Flow in Transformers
- Transformer Interpretability Beyond Attention Visualization
- MambaLRP: Explaining Selective State Space Sequence Models
- MedMamba: Vision Mamba for Medical Image Classification
- Matching Representations of Explainable Artificial Intelligence and Eye Gaze for Human-Machine Interaction
- Human Attention in Fine-grained Classification
- MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs
- LoRA: Low-Rank Adaptation of Large Language Models
- Gaze-Guided Class Activation Mapping: Leveraging Human Attention for Network Attention in Chest X-rays Classification
- GazeGNN: A Gaze-Guided Graph Neural Network for Chest X-ray Classification
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