|
Deng-Bao Wang 王登豹 I am an assistant professor at the School of Computer Science and Engineering, Southeast University. I earned my PhD from Southeast University in 2024, advised by Prof. Min-Ling Zhang. I am a member of PALM group. My research interests mainly include artificial intelligence, machine learning and data mining. I'm currently working on weakly supervised learning and uncertainty calibration of deep models. Additionally, I'm also interested in gaining a deeper understanding of modern neural networks through insightful experiments. Email / Address / Google Scholar / Github |
Selected Publications († denotes equal contribution) |
|
Calibration Bottleneck: Over-compressed Representations are Less Calibratable
Deng-Bao Wang, Min-Ling Zhang International Conference on Machine Learning (ICML), 2024 PDF Code We empirically observed a U-shaped pattern on calibratability of intermediate features, spanning from the lower to the upper layers. |
|
Distilling Reliable Knowledge for Instance-Dependent Partial Label Learning
Dong-Dong Wu†, Deng-Bao Wang†, Min-Ling Zhang AAAI Conference on Artificial Intelligence (AAAI), 2024 PDF Code Appendix |
|
On the Pitfall of Mixup for Uncertainty Calibration
Deng-Bao Wang, Lanqing Li, Peilin Zhao, Pheng-Ann Heng, Min-Ling Zhang IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023 PDF Code Appendix We pointed out the pitfall of Mixup on calibration and propose a simple yet effective strategy named Mixup Inference in Training. |
|
Adaptive Graph Guided Disambiguation for Partial Label Learning
Deng-Bao Wang, Min-Ling Zhang, Li Li IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022 PDF Code Appendix |
|
Revisiting Consistency Regularization for Deep Partial Label Learning
Dong-Dong Wu†, Deng-Bao Wang†, Min-Ling Zhang International Conference on Machine Learning (ICML), 2022 PDF Code |
|
Rethinking Calibration of Deep Neural Networks: Don't Be Afraid of Overconfidence
Deng-Bao Wang, Lei Feng, Min-Ling Zhang Advances in Neural Information Processing Systems (NeurIPS), 2021 PDF Code Appendix We for the first time found that despite those regularized models are better calibrated, they suffer from not being calibratable. |
|
Learning from Complementary Labels via Partial-Output Consistency Regularization
Deng-Bao Wang, Lei Feng, Min-Ling Zhang International Joint Conference on Artificial Intelligence (IJCAI), 2021 PDF Code |
|
Learning from Noisy Labels with Complementary Loss Functions
Deng-Bao Wang, Yong Wen, Lujia Pan, Min-Ling Zhang AAAI Conference on Artificial Intelligence (AAAI), 2021 PDF Code Appendix |
|
Adaptive Graph Guided Disambiguation for Partial Label Learning
Deng-Bao Wang, Li Li, Min-Ling Zhang ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2019 PDF Code |
Honors |
|
DAAD AInet Fellow (2023) National Scholarship (2022, 2018) Tencent Rhino-Bird Elite Training Program (2022) Special Freshman Scholarship for PhD Students (2019) |
Academic Services |
|
Conference program committee member for ICLR (2024, 2025) ICML (2022, 2023, 2024), NeurIPS (2023, 2024), AAAI (2021, 2022, 2024, 2025), IJCAI (2022, 2023, 2024), KDD (2024), etc. Journal reviewer for IEEE TPAMI, IEEE TNNLS, SCIENCE CHINA Information Sciences, ACM TIST, ACM TKDD, IEEE TMM, etc. |