ScorpioBao/Causal-Learning-and-Uncertainty-Estimation

因果学习、不确定性估计相关资源（论文、代码、数据、博客等）

Cusal Learning、Uncertainty Estimation

该站点整理了”因果推理、不确定性估计“相关研究方向的论文、代码、博客等学习资源。

目录

• 因果推理
  • 因果效应评估（Causal Effect Estimation）
  • 因果发现（Causal Discovery）
• 因果表征学习
  • 综述
  • 分布外泛化（Out-of-Distribution Generalization）
  • 稳定学习（Stable Learning）
  • 消除偏差（Debias）
• 不确定性估计
  • 综述
  • 贝叶斯方法（Bayesian）
  • 集成方法（Ensemble）
  • 证据深度学习（Evidential Deep Learning)
• 不确定性估计在不同领域的应用
  • 分割
  • 目标检测
  • 开集识别
  • 分布外泛化
  • 多视图学习
• 深度学习模型校准的相关工作
• 代码和数据集
• 博客
  • 因果推理
  • 不确定性估计
• 交流

一、论文

1、 因果推理(相关论文可以通过目录中的链接访问)

• 计算机视觉中的应用- MaheepChaudhary/Causation-inComputerVision：该存储库包含有关因果关系的论文列表，以及如何使用相关技术来进一步增强深度学习时代的计算机视觉解决方案。 (github.com)

2、 因果表征学习

（1）综述

• Schölkopf, B., Locatello, F., Bauer, S., Ke, N. R., Kalchbrenner, N., Goyal, A., & Bengio, Y. (2021). Toward causal representation learning. Proceedings of the IEEE, 109(5), 612-634.（因果表征学习综述）
• Lu, C., Wu, Y., Hernández-Lobato, J. M., & Schölkopf, B. (2021). Invariant causal representation learning for out-of-distribution generalization. In International Conference on Learning Representations.（不变因果表征学习）

👆 BACK to Table of Contents -->

（2）分布外泛化

相关论文可以在分布外泛化文件夹下查看

• Xu, R., Zhang, X., Shen, Z., Zhang, T., & Cui, P. (2022, June). A Theoretical Analysis on Independence-driven Importance Weighting for Covariate-shift Generalization. In International Conference on Machine Learning (pp. 24803-24829). PMLR.（协变量偏移）
• Liu, C., Sun, X., Wang, J., Tang, H., Li, T., Qin, T., ... & Liu, T. Y. (2021). Learning causal semantic representation for out-of-distribution prediction. Advances in Neural Information Processing Systems, 34, 6155-6170.（因果语义表示学习）
• Zhang, X., Xu, Z., Xu, R., Liu, J., Cui, P., Wan, W., ... & Li, C. (2022). Towards domain generalization in object detection. arXiv preprint arXiv:2203.14387.（目标检测中的域泛化）
• Shen, Z., Liu, J., He, Y., Zhang, X., Xu, R., Yu, H., & Cui, P. (2021). Towards out-of-distribution generalization: A survey. arXiv preprint arXiv:2108.13624.（综述）
• Li, X., Dai, Y., Ge, Y., Liu, J., Shan, Y., & Duan, L. Y. (2022). Uncertainty modeling for out-of-distribution generalization. arXiv preprint arXiv:2202.03958.（OODG不确定性建模）

👆 BACK to Table of Contents -->

（3）稳定学习

相关论文可以在稳定学习文件夹下查看

• Zhang, X., Cui, P., Xu, R., Zhou, L., He, Y., & Shen, Z. (2021). Deep stable learning for out-of-distribution generalization. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 5372-5382).（StableNet）
• Liu, J., Hu, Z., Cui, P., Li, B., & Shen, Z. (2021, July). Heterogeneous risk minimization. In International Conference on Machine Learning (pp. 6804-6814). PMLR.（异质风险最小化）
• Cui, P., & Athey, S. (2022). Stable learning establishes some common ground between causal inference and machine learning. Nature Machine Intelligence, 4(2), 110-115.（稳定学习与因果推断和机器学习之间的共同点）

👆 BACK to Table of Contents -->

（4）消除偏差

• Wang, T., Zhou, C., Sun, Q., & Zhang, H. (2021). Causal attention for unbiased visual recognition. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 3091-3100).（因果注意力）
• Niu, Y., Tang, K., Zhang, H., Lu, Z., Hua, X. S., & Wen, J. R. (2021). Counterfactual vqa: A cause-effect look at language bias. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 12700-12710).（反事实VQA）
• Yang, X., Zhang, H., & Cai, J. (2021). Deconfounded image captioning: A causal retrospect. IEEE Transactions on Pattern Analysis and Machine Intelligence.（去除混淆偏差）
• Nam, J., Cha, H., Ahn, S., Lee, J., & Shin, J. (2020). Learning from failure: De-biasing classifier from biased classifier. Advances in Neural Information Processing Systems, 33, 20673-20684.（从有偏分类器学习去偏分类器）

👆 BACK to Table of Contents -->

3、不确定性估计

（1）综述

• Gawlikowski, J., Tassi, C. R. N., Ali, M., Lee, J., Humt, M., Feng, J., ... & Zhu, X. X. (2021). A survey of uncertainty in deep neural networks. arXiv preprint arXiv:2107.03342.
• Abdar, M., Pourpanah, F., Hussain, S., Rezazadegan, D., Liu, L., Ghavamzadeh, M., ... & Nahavandi, S. (2021). A review of uncertainty quantification in deep learning: Techniques, applications and challenges. Information Fusion, 76, 243-297.
• Uncertainty in Deep Learning（Gal博士论文）
• He, W., & Jiang, Z. (2023). A Survey on Uncertainty Quantification Methods for Deep Neural Networks: An Uncertainty Source Perspective. arXiv preprint arXiv:2302.13425.
• Hüllermeier, E., & Waegeman, W. (2021). Aleatoric and epistemic uncertainty in machine learning: An introduction to concepts and methods. Machine Learning, 110, 457-506.（数据和模型不确定性）

👆 BACK to Table of Contents -->

（2）贝叶斯方法：

• Gal, Y., & Ghahramani, Z. (2016, June). Dropout as a bayesian approximation: Representing model uncertainty in deep learning. In international conference on machine learning (pp. 1050-1059). PMLR.（将Dropout看做贝叶斯近似的经典论文）
• Kendall, A., & Gal, Y. (2017). What uncertainties do we need in bayesian deep learning for computer vision?. Advances in neural information processing systems, 30.（不确定性估计必读论文，将不确定性分为数据不确定性以及模型不确定性，并介绍了在分类和回归中不确定性估计的建模方法）
• Louizos, C., & Welling, M. (2017, July). Multiplicative normalizing flows for variational bayesian neural networks. In International Conference on Machine Learning (pp. 2218-2227). PMLR.（变分贝叶斯神经网络，EDL论文中的对比方法）

👆 BACK to Table of Contents -->

（3）集成方法

• Lakshminarayanan, B., Pritzel, A., & Blundell, C. (2017). Simple and scalable predictive uncertainty estimation using deep ensembles. Advances in neural information processing systems, 30.（集成方法的开山之作）

👆 BACK to Table of Contents -->

（4）证据深度学习

• Sensoy, M., Kaplan, L., & Kandemir, M. (2018). Evidential deep learning to quantify classification uncertainty. Advances in neural information processing systems, 31.（证据分类）
• Amini, A., Schwarting, W., Soleimany, A., & Rus, D. (2020). Deep evidential regression. Advances in Neural Information Processing Systems, 33, 14927-14937.（证据回归）
• Sensoy, M., Kaplan, L., Cerutti, F., & Saleki, M. (2020, April). Uncertainty-aware deep classifiers using generative models. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 34, No. 04, pp. 5620-5627).（EDL作者的另一篇论文）
• Malinin, A., & Gales, M. (2018). Predictive uncertainty estimation via prior networks. Advances in neural information processing systems, 31.（使用狄利克雷分布建模不确定性的另一种方法）
• Ulmer, D. (2021). A survey on evidential deep learning for single-pass uncertainty estimation. arXiv preprint arXiv:2110.03051.（证据不确定性综述）
• Zhao, X., Ou, Y., Kaplan, L., Chen, F., & Cho, J. H. (2019). Quantifying classification uncertainty using regularized evidential neural networks. arXiv preprint arXiv:1910.06864.（证据基础上添加正则化项）

👆 BACK to Table of Contents -->

4、不确定性估计在不同领域的应用

（1）分割

• Kwon, Y., Won, J. H., Kim, B. J., & Paik, M. C. (2020). Uncertainty quantification using Bayesian neural networks in classification: Application to biomedical image segmentation. Computational Statistics & Data Analysis, 142, 106816.（贝叶斯不确定性）
• Li, H., Nan, Y., Del Ser, J., & Yang, G. (2022). Region-based evidential deep learning to quantify uncertainty and improve robustness of brain tumor segmentation. Neural Computing and Applications, 1-15.（证据不确定性）
• Zou, K., Yuan, X., Shen, X., Chen, Y., Wang, M., Goh, R. S. M., ... & Fu, H. (2023). EvidenceCap: Towards trustworthy medical image segmentation via evidential identity cap. arXiv preprint arXiv:2301.00349.（证据不确定性）
• Zhou, X., Yue, X., Xu, Z., Denoeux, T., & Chen, Y. (2021, December). Deep neural networks with prior evidence for bladder cancer staging. In 2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) (pp. 1221-1226). IEEE.（证据医学影像分割）

👆 BACK to Table of Contents -->

（2）目标检测

• Harakeh, A., Smart, M., & Waslander, S. L. (2020, May). Bayesod: A bayesian approach for uncertainty estimation in deep object detectors. In 2020 IEEE International Conference on Robotics and Automation (ICRA) (pp. 87-93). IEEE.（目标检测中的贝叶斯不确定性估计）
• Feng, D., Harakeh, A., Waslander, S. L., & Dietmayer, K. (2021). A review and comparative study on probabilistic object detection in autonomous driving. IEEE Transactions on Intelligent Transportation Systems, 23(8), 9961-9980.（自动驾驶中的概率目标检测）
• Hang, Q., Li, Z., Dong, Y., & Yue, X. (2022, November). Uncertainty-Aware Deep Open-Set Object Detection. In Rough Sets: International Joint Conference, IJCRS 2022, Suzhou, China, November 11–14, 2022, Proceedings (pp. 161-175). Cham: Springer Nature Switzerland.（证据目标检测）
• Miller, D. (2021). Epistemic uncertainty estimation for object detection in open-set conditions (Doctoral dissertation, Queensland University of Technology).（开集目标检测）
• Gasperini, S., Haug, J., Mahani, M. A. N., Marcos-Ramiro, A., Navab, N., Busam, B., & Tombari, F. (2021). CertainNet: Sampling-free uncertainty estimation for object detection. IEEE Robotics and Automation Letters, 7(2), 698-705.（基于Centernet的不确定度量）
• Nallapareddy, M. R., Sirohi, K., Drews-Jr, P. L., Burgard, W., Cheng, C. H., & Valada, A. (2023). EvCenterNet: Uncertainty Estimation for Object Detection using Evidential Learning. arXiv preprint arXiv:2303.03037.(证据深度学习目标检测，基于Centernet)
• He, Y., Zhu, C., Wang, J., Savvides, M., & Zhang, X. (2019). Bounding box regression with uncertainty for accurate object detection. In Proceedings of the ieee/cvf conference on computer vision and pattern recognition (pp. 2888-2897).（回归不确定性目标检测）

👆 BACK to Table of Contents -->

（3）开集识别

• Bao, W., Yu, Q., & Kong, Y. (2021). Evidential deep learning for open set action recognition. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 13349-13358).（开集识别）
• Corbière, C., Lafon, M., Thome, N., Cord, M., & Pérez, P. (2021, September). Beyond First-Order Uncertainty Estimation with Evidential Models for Open-World Recognition. In ICML 2021 Workshop on Uncertainty and Robustness in Deep Learning.（正则化项）
• Corbière, C., Lafon, M., Thome, N., Cord, M., & Pérez, P. (2021, September). Beyond First-Order Uncertainty Estimation with Evidential Models for Open-World Recognition. In ICML 2021 Workshop on Uncertainty and Robustness in Deep Learning.（证据用于开放世界识别）
• Mundt, M., Pliushch, I., Majumder, S., & Ramesh, V. (2019). Open set recognition through deep neural network uncertainty: Does out-of-distribution detection require generative classifiers?. In Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops.（OOD检测）
• Zhou, T., Han, T., & Droguett, E. L. (2022). Towards trustworthy machine fault diagnosis: A probabilistic Bayesian deep learning framework. Reliability Engineering & System Safety, 224, 108525.（贝叶斯故障诊断）

👆 BACK to Table of Contents -->

（4）分布外泛化

• Chen, L., Lou, Y., He, J., Bai, T., & Deng, M. (2022, June). Evidential neighborhood contrastive learning for universal domain adaptation. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 36, No. 6, pp. 6258-6267).（证据领域对比学习）
• Qiao, F., & Peng, X. (2021). Uncertainty-guided model generalization to unseen domains. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 6790-6800).（不确定性指导的数据增广）
• Zhao, L., Liu, T., Peng, X., & Metaxas, D. (2020). Maximum-entropy adversarial data augmentation for improved generalization and robustness. Advances in Neural Information Processing Systems, 33, 14435-14447.（对抗数据增广-最大熵）
• Li, X., Dai, Y., Ge, Y., Liu, J., Shan, Y., & Duan, L. Y. (2022). Uncertainty modeling for out-of-distribution generalization. arXiv preprint arXiv:2202.03958.（OODG的不确定性建模）

👆 BACK to Table of Contents -->

（5）多视图学习

• Han, Z., Zhang, C., Fu, H., & Zhou, J. T. (2022). Trusted multi-view classification with dynamic evidential fusion. IEEE transactions on pattern analysis and machine intelligence.（证据多视图分类）
• Ma, H., Han, Z., Zhang, C., Fu, H., Zhou, J. T., & Hu, Q. (2021). Trustworthy multimodal regression with mixture of normal-inverse gamma distributions. Advances in Neural Information Processing Systems, 34, 6881-6893.（证据多模态回归）
• Geng, Y., Han, Z., Zhang, C., & Hu, Q. (2021, May). Uncertainty-aware multi-view representation learning. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 35, No. 9, pp. 7545-7553).（多视图回归-数据不确定性建模）
• Zhang, Q., Wu, H., Zhang, C., Hu, Q., Fu, H., Zhou, J. T., & Peng, X. (2023). Provable Dynamic Fusion for Low-Quality Multimodal Data. arXiv preprint arXiv:2306.02050.（基于能量函数的不确定性估计）

👆 BACK to Table of Contents -->

5、深度学习模型校准的相关工作

• Guo, C., Pleiss, G., Sun, Y., & Weinberger, K. Q. (2017, July). On calibration of modern neural networks. In International conference on machine learning (pp. 1321-1330). PMLR.（分类校准）
• Kuleshov, V., Fenner, N., & Ermon, S. (2018, July). Accurate uncertainties for deep learning using calibrated regression. In International conference on machine learning (pp. 2796-2804). PMLR.（回归校准）
• Mukhoti, J., Kulharia, V., Sanyal, A., Golodetz, S., Torr, P., & Dokania, P. (2020). Calibrating deep neural networks using focal loss. Advances in Neural Information Processing Systems, 33, 15288-15299.（Focal Loss 校准分类）
• Krishnan, R., & Tickoo, O. (2020). Improving model calibration with accuracy versus uncertainty optimization. Advances in Neural Information Processing Systems, 33, 18237-18248.（考虑不确定性校准模型）
• Thulasidasan, S., Chennupati, G., Bilmes, J. A., Bhattacharya, T., & Michalak, S. (2019). On mixup training: Improved calibration and predictive uncertainty for deep neural networks. Advances in Neural Information Processing Systems, 32.（mixup提高模型校准性能）

👆 BACK to Table of Contents -->

二、代码和数据集

相关论文的代码以及数据集可以在Paper With Code 搜索获取，如果Paper With Code 中没有收录，可直接在GitHub输入论文关键字搜索相关代码

👆 BACK to Table of Contents -->

三、博客

1、因果推理

• e-CARE: 可解释的因果推理评测 (qq.com)
• 【Valse - 崔鹏】Out-of-Distribution 分布外泛化 - 知乎 (zhihu.com)
• 崔鹏团队：万字长文梳理「稳定学习」全景图 - 知乎 (zhihu.com)
• 【综述】离群/异常/新类检测？开集识别？分布外检测？一文搞懂其间异同！ - 知乎 (zhihu.com)
• 因果表征学习最新综述：连接因果科学和机器学习的桥梁 - 知乎 (zhihu.com)
• 因果推断：因果表征学习的CV落地 - 知乎 (zhihu.com)

👆 BACK to Table of Contents -->

2、不确定性估计

• (184条消息) What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision? 计算机视觉用于贝叶斯深度学习的不确定性_Xieyuanli_Chen的博客-CSDN博客
• Bayesian inference problem, MCMC and variational inference | by Joseph Rocca | Towards Data Science
• Uncertainty Estimation in CV - 知乎 (zhihu.com)
• What my deep model doesn't know... | Yarin Gal - Blog | Oxford Machine Learning
• Uncertainty in Deep Learning. How To Measure? | Towards Data Science
• https://www.bilibili.com/video/BV1RJ411D7QA/
• 如何创造可信任的机器学习模型？先要理解不确定性 (qq.com)
• 从最大似然到EM算法：一致的理解方式 - 科学空间|Scientific Spaces (kexue.fm)
• ICML高引模型校准论文，一个好的工作是怎样的 - 知乎 (zhihu.com)

👆 BACK to Table of Contents -->

四、交流

• Email: senlinbao@gmail.com