Visual Explanations for Convolutional Neural Networks via Input Resampling

By Benjamin J. Lengerich, Sandeep Konam, Eric P. Xing, Stephanie Rosenthal, Manuela M. Veloso. 2017

21 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Quanshi Zhang
2. Song-Chun Zhu
3. Ying Nian Wu
4. Giulia Vilone
5. Yu Yang
6. Longo Luca
7. Jianwen Xie
8. Erik Nijkamp

Citations in the corpus

• Unsupervised Learning of Neural Networks to Explain Neural Networks (2018, background): “Other studies retrieved mid-level representations with specific meanings from CNNs for various applications [15, 35, 32, 19].”
• Interpretable Convolutional Neural Networks (2017, background): “[11, 31, 29, 15] selected neural units with specific meanings from CNNs for various applications.”
• Grad-CAM++: Generalized Gradient-Based Visual Explanations for Deep Convolutional Networks (2017, background): “[7] proposed a different route towards explainability of CNNs.”
• Explainable Artificial Intelligence: a Systematic Review (2020, methodology): “The Important Neurons and Patches method [221] analyzes the predictions of a DNN in terms of its internal features by inspecting information flow through the network.”