Poly-cam: high resolution class activation map for convolutional neural networks
(2024) Machine Vision & Applications — Vol. 35, n° 4, p. 89 [1-16] (2024)
Files
2024_Englebert_Mach_Vis_Appl.pdf
Open Access - Adobe PDF
- 8.6 MB
Details
- Authors
- Abstract
- The demand for explainable AI continues to rise alongside advancements in deep learning technology. Existing methods such as convolutional neural networks often struggle to accurately pinpoint the image features justifying a network’s prediction due to low-resolution saliency maps (e.g., CAM), smooth visualizations from perturbation-based techniques, or numerous isolated peaky spots in gradient-based approaches. In response, our work seeks to merge information from earlier and later layers within the network to create high-resolution class activation maps that not only maintain a level of competitiveness with previous art in terms of insertion-deletion faithfulness metrics but also significantly surpass it regarding the precision in localizing class-specific features.
- Affiliations
Citations
Englebert, A., Cornu, O., & De Vleeschouwer, C. (2024). Poly-cam: high resolution class activation map for convolutional neural networks. Machine Vision & Applications, 35(4), 89 [1-16]. https://doi.org/10.1007/s00138-024-01567-7 (Original work published 2024)