| Interpreting multivariate shapley interactions in dnns H Zhang, Y Xie, L Zheng, D Zhang, Q Zhang Proceedings of the AAAI Conference on Artificial Intelligence 35 (12), 10877 …, 2021 | 53 | 2021 |
| Discovering and explaining the representation bottleneck of dnns H Deng, Q Ren, H Zhang, Q Zhang arXiv preprint arXiv:2111.06236, 2021 | 52 | 2021 |
| Interpreting and boosting dropout from a game-theoretic view H Zhang, S Li, Y Ma, M Li, Y Xie, Q Zhang arXiv preprint arXiv:2009.11729, 2020 | 46 | 2020 |
| Interpretable complex-valued neural networks for privacy protection L Xiang, H Ma, H Zhang, Y Zhang, J Ren, Q Zhang arXiv preprint arXiv:1901.09546, 2019 | 37 | 2019 |
| Interpreting attributions and interactions of adversarial attacks X Wang, S Lin, H Zhang, Y Zhu, Q Zhang Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2021 | 12 | 2021 |
| Game-theoretic interactions of different orders H Zhang, X Cheng, Y Chen, Q Zhang arXiv preprint arXiv:2010.14978, 2020 | 12 | 2020 |
| Towards a unified evaluation of explanation methods without ground truth H Zhang, J Chen, H Xue, Q Zhang arXiv preprint arXiv:1911.09017, 2019 | 12 | 2019 |
| Quantification and analysis of layer-wise and pixel-wise information discarding H Ma, H Zhang, F Zhou, Y Zhang, Q Zhang arXiv preprint arXiv:1906.04109, 2019 | 1 | 2019 |
