• KSII Transactions on Internet and Information Systems
    Monthly Online Journal (eISSN: 1976-7277)

GIG-CAM+M: A Class Activation Mapping Method Incorporating Guided Integrated Gradients and Multi-scale Strategy

Vol. 19, No. 4, April 30, 2025
10.3837/tiis.2025.04.004, Download Paper (Free):

Abstract

The interpretability of convolutional neural networks has garnered widespread attention, with class activation mapping (CAM)-based methods emerging as a prominent research direction. Integrated Grad-CAM is a widely used backpropagation-based CAM method, but its use of a linear path introduces noise during the integration process. To address this issue, we propose GIG-CAM, which replaces the linear path with an adaptive path. Unlike previous methods that require path specification, GIG-CAM dynamically determines the next input in the path based on saliency maps. Additionally, to enhance the resolution of saliency maps, we introduce a novel multi-scale fusion method, which recursively optimizes saliency maps at smaller scales using saliency maps at larger scales. This preserves the localization capability of the original-scale saliency maps while enhancing their resolution. Experimental results on the VOC2012 and ILSVRC2012 datasets demonstrate that GIG-CAM with fusion (GIG-CAM(F)) outperforms existing methods, achieving the highest scores in the Pointing Game (82.80% and 85.90% on ResNet50 for VOC2012 and ILSVRC2012, respectively) and Energy-Based Pointing Game (62.41% and 59.69%, respectively). Furthermore, GIG-CAM(F) achieves the lowest Drop% (22.59% and 17.04%) and highest Increase% (31.00% and 21.95%), validating its superior interpretability. Our results highlight the effectiveness of GIG-CAM in improving the quality and reliability of saliency maps, making it a robust solution for enhancing deep model transparency.


Statistics

Show / Hide Statistics

Statistics (Cumulative Counts from December 1st, 2015)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article

[IEEE Style]
Y. Gao, X. Miao, G. Zhang, "GIG-CAM+M: A Class Activation Mapping Method Incorporating Guided Integrated Gradients and Multi-scale Strategy," KSII Transactions on Internet and Information Systems, vol. 19, no. 4, pp. 1122-1139, 2025. DOI: 10.3837/tiis.2025.04.004.

[ACM Style]
Yanfei Gao, Xiongwei Miao, and Guoye Zhang. 2025. GIG-CAM+M: A Class Activation Mapping Method Incorporating Guided Integrated Gradients and Multi-scale Strategy. KSII Transactions on Internet and Information Systems, 19, 4, (2025), 1122-1139. DOI: 10.3837/tiis.2025.04.004.

[BibTeX Style]
@article{tiis:102444, title="GIG-CAM+M: A Class Activation Mapping Method Incorporating Guided Integrated Gradients and Multi-scale Strategy", author="Yanfei Gao and Xiongwei Miao and Guoye Zhang and ", journal="KSII Transactions on Internet and Information Systems", DOI={10.3837/tiis.2025.04.004}, volume={19}, number={4}, year="2025", month={April}, pages={1122-1139}}