• Corpus ID: 208006714

Improve Model Generalization and Robustness to Dataset Bias with Bias-regularized Learning and Domain-guided Augmentation

@article{Zhang2019ImproveMG,
  title={Improve Model Generalization and Robustness to Dataset Bias with Bias-regularized Learning and Domain-guided Augmentation},
  author={Yundong Zhang and Hang Wu and Huiye Liu and Li Tong and May D. Wang},
  journal={arXiv: Image and Video Processing},
  year={2019}
}
Deep Learning has thrived on the emergence of biomedical big data. However, medical datasets acquired at different institutions have inherent bias caused by various confounding factors such as operation policies, machine protocols, treatment preference and etc. As the result, models trained on one dataset, regardless of volume, cannot be confidently utilized for the others. In this study, we investigated model robustness to dataset bias using three large-scale Chest X-ray datasets: first, we… 
3 Citations
Deep Mining External Imperfect Data for Chest X-Ray Disease Screening
TLDR
This paper argues that incorporating an external CXR dataset leads to imperfect training data, which raises the challenges, and formulate the multi-label thoracic disease classification problem as weighted independent binary tasks according to the categories, enabling superior knowledge mining ability.
Computer-aided abnormality detection in chest radiographs in a clinical setting via domain-adaptation
TLDR
The experimental results show the proposed domain-shift detection and removal method’s effectiveness in deploying a pre-trained DL model for abnormality detection in chest radiographs in a clinical setting.
Image Analysis and Recognition: 17th International Conference, ICIAR 2020, Póvoa de Varzim, Portugal, June 24–26, 2020, Proceedings, Part II
TLDR
A cosine-weighted FDA as well as an automatically weighted FDA in which weights are found automatically are proposed in the feature space to establish a weighted kernel FDA for both existing and newly proposed weights.