1 code implementation • 26 Jul 2023 • Fengchun Qiao, Xi Peng
Out-of-distribution (OOD) generalization is a challenging machine learning problem yet highly desirable in many high-stake applications.
1 code implementation • CVPR 2023 • Tang Li, Fengchun Qiao, Mengmeng Ma, Xi Peng
How to develop robust explanations against out-of-distribution data?
no code implementations • 29 Sep 2021 • Fengchun Qiao, Xi Peng
The key idea is to estimate the density ratio between the distributions of the two modalities, and use it to calibrate the similarity measurement in the embedding space.
no code implementations • 5 Aug 2021 • Xi Peng, Fengchun Qiao, Long Zhao
We are concerned with a worst-case scenario in model generalization, in the sense that a model aims to perform well on many unseen domains while there is only one single domain available for training.
no code implementations • CVPR 2021 • Fengchun Qiao, Xi Peng
To the best of our knowledge, this is the first work to (1) access the generalization uncertainty from a single source and (2) leverage it to guide both input and label augmentation for robust generalization.
no code implementations • 1 Jan 2021 • Fengchun Qiao, Xi Peng
To the best of our knowledge, this is the first work to (1) access the generalization uncertainty from a single source and (2) leverage it to guide both input and label augmentation for robust generalization.
1 code implementation • CVPR 2020 • Fengchun Qiao, Long Zhao, Xi Peng
We are concerned with a worst-case scenario in model generalization, in the sense that a model aims to perform well on many unseen domains while there is only one single domain available for training.
1 code implementation • 6 Feb 2018 • Fengchun Qiao, Naiming Yao, Zirui Jiao, Zhihao LI, Hui Chen, Hongan Wang
Geometry information is introduced into cGANs as continuous conditions to guide the generation of facial expressions.