Research and Publicationis
2023
Margin as an Effective Confidence Score for SelectiveClassification under Distribution Shifts
Hengyue Liang, Le Peng, Ju Sun
Under review for “Artificial Intelligence and Statistics 2024” (AISTATS)
Rethink Transfer Learning in Medical Image Classification.
Le Peng, Hengyue Liang, Taihui Li, Ju Sun
Accepted to British Machine Vision Conference (BMVC), 2024 (Oral)
Automated Quantification of Eye Tics using Computer Vision and Deep Learning Techniques
Christine Conelea, Hengyue Liang, Megan DuBois, Brittany Raab, Mia Kellman, Brianna Wellen, Suma Jacob, Sonya Wang, Ju Sun and Kelvin Lim
Under review for “Movement Disorders”, the official Journal of Movement Disorder Society (MDS), MDS-23-0240.R1
Optimization and optimizers for adversarial robustness
Hengyue Liang, Buyun Liang, Le Peng, Ying Cui, Tim Mitchell, Ju Sun
In preparation for “International Journal of Computer Vision” (IJCV)
Implications of Solution Patterns on Adversarial Robustness.
Hengyue Liang, Buyun Liang, Ying Cui, Tim Mitchell, Ju Sun
Accepted to “Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition” (CVPR 2023, workshop of adversarial machine learning)
2022
Optimization for Robustness Evaluation beyond ℓp Metrics.
Hengyue Liang, Buyun Liang, Ying Cui, Tim Mitchell, Ju Sun
Accepted to “2023 IEEE International Conference on Acoustics, Speech, and Signal Processing” (ICASSP)
2021
Early Stopping for Deep Image Prior.
Hengkang Wang, Taihui Li, Zhong Zhuang, Tiancong Chen, Hengyue Liang, Ju Sun
Self-Validation: Early Stopping for Single-Instance Deep Generative Priors.
Taihui Li, Zhong Zhuang, Hengyue Liang, Le Peng, Hengkang Wang, Ju Sun.
Accepted to British Machine Vision Conference (BMVC) 2021.
2020
Learning Visual Affordances with Target-Orientated Deep Q-Network to Grasp Objects by Harnessing Environmental Fixtures.
Hengyue Liang, Xibai Lou, Yang Yang, Changhyun Choi
Accepted to IEEE International Conference on Robotics and Automation (ICRA) 2021, Xi'an
Attribute-Based Robotic Grasping with One-Grasp Adaptation.
Yang Yang, Yuanhao Liu, Hengyue Liang, Xibai Lou and Changhyun Choi
Accepted to IEEE International Conference on Robotics and Automation (ICRA) 2021, Xi'an
2019
A Deep Learning Approach to Grasping the Invisible.
Yang Yang, Hengyue Liang and Changhyun Choi
Accepted to IEEE Robotics and Automation Letters (RA-L) 2020