.png){kind=icon}
返回
Activation Map-Based Visual Explanation for Remote Sensing Image Super-Resolution
.png){kind=icon}
PRE
AI
DOI：10.1109/LGRS.2026.3657185.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Deep learning has enhanced image super-resolution (SR) performance, yet SR networks are often treated as closed boxes with limited explainability. Notably, remote sensing (RS) images possess explicit physical semantics, imposing stringent demands on the explainability of their SR methods. To address this, we propose AMVE-SR, a framework that systematically transfers activation map-based visual explanation (AMVE) from classification networks to SR networks. Distinct from classification-oriented methods (e.g., Grad-CAM) that struggle with shallow-layer visualization or computationally intensive perturbation-based approaches, AMVE-SR introduces a layer-wise recursive propagation mechanism. By exploiting interlayer correlations, it traces activation maps backward to the input, ensuring high-fidelity explanations even in shallow layers where conventional methods fail to transfer effectively. Furthermore, we compute gradient responses via textural discrepancy rather than raw pixel intensities, capturing high-frequency details (e.g., physical boundaries) essential for physical semantics. To address the lack of quantitative metrics, we propose average texture variation (ATV) by adapting the average drop concept in classification tasks. Validated by visual consistency, ATV serves as a novel fidelity metric for SR explanations. Experiments on the AID dataset using the EDSR model demonstrate that our method produces visually reliable explanation maps while achieving superior performance on the proposed ATV metric with high running efficiency. In general, this study extends AMVE from image classification to SR, thereby establishing a new paradigm to explain SR networks.
Keyword:
Activation map-based visual explanation (AMVE)
class activation maps (CAMs)
remote sensing (RS) images
super-resolution (SR)
期刊
I
IF:
4.4
论文数:
715
被引数:
0
机构
引用论文
Grad-CAM++: Generalized Gradient-Based Visual Explanations for Deep Convolutional NetworksGrad-cam: 基于广义梯度的深度卷积网络视觉解释
OAAI
OAAI分享收藏A review of deep-learning-based super-resolution: From methods to applications基于深度学习的超分辨率研究综述: 从方法到应用.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural NetworksScore-CAM: 卷积神经网络的分数加权视觉解释OAAI
OAAI分享收藏CIFAKE: Image Classification and Explainable Identification of AI-Generated Synthetic ImagesCIFAKE: 图像分类和AI生成的合成图像的可解释识别IEEE ACCESS
OAAI
IEEE ACCESSIF3.6
OAAI分享收藏
查看更多内容