Research
Adversarially Robust Learning-to-Defer for Classification and Regression
Extend the robustness framework of Montreuil et al. (2025a) to one-stage scenario, where considering the interaction between learning the predictor and adapting the experts.
Collaborator & Supervisor: Yannis Montreuil
Road Sign Classification with Denoising Pipeline Approach.
Real-world images are affected by image noise, which degrades the quality and reduces reliability of traffic sign recognition. This research proposes a denoiser-classifier pipeline approach, which uses a pre-trained color image denoiser, and compares it against an end-to-end approach. We evaluated CNN and ResNet-18 on GTSRB under Gaussian noise.
Collaborators: Yuqi Sun, Jiaqi Zhang, Huayu Liu, Zhuoyang Hu
Supervisor: Professor David Woodruff