/AMAZING_XAI

Top conference papers & top journal papers on Explainable/Interpretable AI (XAI)

AMAZING_XAI

1. A book to have a overall understanding of XAI

2. PhD thesis

  • (Zhou Bolei) Interpretable Representation Learning for Visual Intelligence [thesis]
  • (Been Kim) Interactive and Interpretable Machine Learning Models for Human Machine Collaboration [thesis]

3. General XAI

4. XAI for CV

4.1. Deconvolution

  • Zeiler, Matthew D., and Rob Fergus. "Visualizing and understanding convolutional networks." European conference on computer vision. Springer, Cham, 2014. [paper]

4.2. Class Model Visualisation & Image-Specific Class Saliency Visualisation

  • Simonyan, Karen, Andrea Vedaldi, and Andrew Zisserman. "Deep inside convolutional networks: Visualising image classification models and saliency maps." arXiv preprint arXiv:1312.6034 (2013). [paper]

4.3. Simplify the input image & Visualize the receptive fields & Emergence of objects as the internal representation

  • Zhou, Bolei, et al. "Object detectors emerge in deep scene cnns." arXiv preprint arXiv:1412.6856 (2014). [paper] [related dataset: Places]

4.4. Two kinds of uncertainty: aleatoric uncertainty & epistemic uncertainty

  • Kendall, Alex, and Yarin Gal. "What uncertainties do we need in bayesian deep learning for computer vision?." Advances in neural information processing systems. 2017. [paper] [related datasets: CamVid, NYU v2, Make3D]
  • (About Bayesian Neural Networks, see Blundell, Charles, et al. "Weight uncertainty in neural networks." arXiv preprint arXiv:1505.05424 (2015). [paper] Also see a github repository Bayesian-Neural-Networks.)