English

Mixing-AdaSIN: Constructing a De-biased Dataset using Adaptive Structural Instance Normalization and Texture Mixing

Image and Video Processing 2021-08-03 v2 Computer Vision and Pattern Recognition

Abstract

Following the pandemic outbreak, several works have proposed to diagnose COVID-19 with deep learning in computed tomography (CT); reporting performance on-par with experts. However, models trained/tested on the same in-distribution data may rely on the inherent data biases for successful prediction, failing to generalize on out-of-distribution samples or CT with different scanning protocols. Early attempts have partly addressed bias-mitigation and generalization through augmentation or re-sampling, but are still limited by collection costs and the difficulty of quantifying bias in medical images. In this work, we propose Mixing-AdaSIN; a bias mitigation method that uses a generative model to generate de-biased images by mixing texture information between different labeled CT scans with semantically similar features. Here, we use Adaptive Structural Instance Normalization (AdaSIN) to enhance de-biasing generation quality and guarantee structural consistency. Following, a classifier trained with the generated images learns to correctly predict the label without bias and generalizes better. To demonstrate the efficacy of our method, we construct a biased COVID-19 vs. bacterial pneumonia dataset based on CT protocols and compare with existing state-of-the-art de-biasing methods. Our experiments show that classifiers trained with de-biased generated images report improved in-distribution performance and generalization on an external COVID-19 dataset.

Keywords

Cite

@article{arxiv.2103.14255,
  title  = {Mixing-AdaSIN: Constructing a De-biased Dataset using Adaptive Structural Instance Normalization and Texture Mixing},
  author = {Myeongkyun Kang and Philip Chikontwe and Miguel Luna and Kyung Soo Hong and June Hong Ahn and Sang Hyun Park},
  journal= {arXiv preprint arXiv:2103.14255},
  year   = {2021}
}
R2 v1 2026-06-24T00:34:37.456Z