1. Selvaraju, Ramprasaath R., et al. "Grad-cam: Visual explanations from deep networks via gradient-based localization." Proceedings of the IEEE international conference on computer vision. 2017.

  2. Grad-CAM implementation in Keras[Source code]. https://github.com/jacobgil/keras-grad-cam.

  3. Sundararajan, Mukund, Ankur Taly, and Qiqi Yan. "Axiomatic attribution for deep networks." International Conference on Machine Learning. PMLR, 2017.

  4. Integrated Gradients[Source code]. https://github.com/hiranumn/IntegratedGradients.

  5. @inproceedings{karkkainenfairface, title={FairFace: Face Attribute Dataset for Balanced Race, Gender, and Age for Bias Measurement and Mitigation}, author={Karkkainen, Kimmo and Joo, Jungseock}, booktitle={Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision}, year={2021}, pages={1548--1558}}

  6. FairFace: Face Attribute Dataset for Balanced Race, Gender, and Age[Source code]. https://github.com/dchen236/FairFace.
  7. Draelos, Rachel. “Grad-CAM: Visual Explanations from Deep Networks.” Glass Box, 29 May 2020. https://glassboxmedicine.com/2020/05/29/grad-cam-visual-explanations-from-deep-networks/#:~:text=Grad%2DCAM%20can%20be%20used%20for%20understanding%20a%20model's%20predictions,choice%20than%20Guided%20Grad%2DCAM.