no code implementations • 23 Mar 2023 • Hengyue Liang, Buyun Liang, Le Peng, Ying Cui, Tim Mitchell, Ju Sun
Taking advantage of PWCF and other existing numerical algorithms, we further explore the distinct patterns in the solutions found for solving these optimization problems using various combinations of losses, perturbation models, and optimization algorithms.
no code implementations • 2 Oct 2022 • Hengyue Liang, Buyun Liang, Ying Cui, Tim Mitchell, Ju Sun
Empirical evaluation of deep learning models against adversarial attacks entails solving nontrivial constrained optimization problems.
1 code implementation • 11 Dec 2021 • Hengkang Wang, Taihui Li, Zhong Zhuang, Tiancong Chen, Hengyue Liang, Ju Sun
In this regard, the majority of DIP works for vision tasks only demonstrates the potential of the models -- reporting the peak performance against the ground truth, but provides no clue about how to operationally obtain near-peak performance without access to the groundtruth.
2 code implementations • 23 Oct 2021 • Taihui Li, Zhong Zhuang, Hengyue Liang, Le Peng, Hengkang Wang, Ju Sun
Recent works have shown the surprising effectiveness of deep generative models in solving numerous image reconstruction (IR) tasks, even without training data.
2 code implementations • 9 Jun 2021 • Le Peng, Hengyue Liang, Gaoxiang Luo, Taihui Li, Ju Sun
Transfer learning (TL) from pretrained deep models is a standard practice in modern medical image classification (MIC).
no code implementations • 6 Apr 2021 • Yang Yang, YuanHao Liu, Hengyue Liang, Xibai Lou, Changhyun Choi
In this work, we introduce an end-to-end learning method of attribute-based robotic grasping with one-grasp adaptation capability.
no code implementations • 9 Oct 2019 • Hengyue Liang, Xibai Lou, Yang Yang, Changhyun Choi
This Slide-to-Wall grasping task assumes no prior knowledge except the partial observation of a target object.
1 code implementation • 11 Sep 2019 • Yang Yang, Hengyue Liang, Changhyun Choi
The target-oriented motion critic, which maps both visual observations and target information to the expected future rewards of pushing and grasping motion primitives, is learned via deep Q-learning.