方堃 Kun FANG

方堃 Kun FANG

Postdoctoral Fellow

Selected Publications

Here lists a part of my publications on kernels, adversarial learning and out-of-distribution detection. You can find a full collection of my articles on my Google Scholar profile.

Preprint

Kernel PCA for Out-of-Distribution Detection: Non-Linear Kernel Selections and Approximations. arxiv, code
Kun Fang, Qinghua Tao, Mingzhen He, Kexin Lv, Runze Yang, Haibo Hu, Xiaolin Huang, Jie Yang, Longbin Cao

Beyond Perceptual Distances: Rethinking Disparity Assessment for Out-of-Distribution Detection with Diffusion models. arxiv
Kun Fang, Qinghua Tao, Zuopeng Yang, Xiaolin Huang, Jie Yang

Conferences

Kernel PCA for Out-of-Distribution Detection
Kun Fang, Qinghua Tao, Kexin Lv, Mingzhen He, Xiaolin Huang, Jie Yang
Conference on Advances in Neural Information Processing Systems (NeurIPS) , 2024. conf., arxiv, code

Journals

Multi-head Ensemble of Smoothed Classifiers for Certified Robustness
Kun Fang, Qinghua Tao, Yingwen Wu, Tao Li, Xiaolin Huang, Jie Yang
Neural Networks, 2025. journal, arxiv, code

Revisiting Deep Ensemble for Out-of-Distribution Detection: A Loss Landscape Perspective
Kun Fang, Qinghua Tao, Xiaolin Huang, Jie Yang
International Journal of Computer Vision, 2024. journal, arxiv, code

Towards Robust Neural Networks via Orthogonal Diversity
Kun Fang, Qinghua Tao, Yingwen Wu, Tao Li, Jia Cai, Feipeng Cai, Xiaolin Huang, Jie Yang
Pattern Recognition, 2024. journal, arxiv, code

End-to-end Kernel Learning via Generative Random Fourier Features
Kun Fang, Fanghui Liu, Xiaolin Huang, Jie Yang
Pattern Recognition, 2023. journal, arxiv, code

Papers I have co-authored

Adaptive distillation on hard samples benefits consistency for certified robustness
Jiawen Li, Kun Fang, Jie Yang
International Journal of Machine Learning and Cybernetics, 2025. journal

Boosting Certified Robustness via An Expectation-based Similarity Regularization
Jiawen Li, Kun Fang, Xiaolin Huang, Jie Yang
Image and Vision Computing, 2024. journal

Improving Adversarial Robustness through A Curriculum-guided Reliable Distillation
Jiawen Li, Kun Fang, Xiaolin Huang, Jie Yang
Computers & Security, 2023. journal, code

Improving the Adversarial Robustness of Quantized Neural Networks via Exploiting the Feature Diversity
Tianshu Chu, Kun Fang, Jie Yang, Xiaolin Huang
Pattern Recognition Letters, 2023. journal

Unifying Gradients to Improve Real-world Robustness for Deep Networks.
Yingwen Wu, Sizhe Chen, Kun Fang, Xiaolin Huang
ACM Transactions on Intelligent Systems and Technology, 2023. journal, arxiv, code

Subspace Adversarial Learning.
Tao Li, Yingwen Wu, Sizhe Chen, Kun Fang, Xiaolin Huang
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022. conf., arxiv, code