@inproceedings{blunk2025adaptive,
    type = {inproceedings},
    key = {blunk2025adaptive},
    author = {Jan Blunk and Paul Bodesheim and Joachim Denzler},
    title = {Adaptive Model Selection for Expanded Post Hoc Debiasing and Mitigating Varying Degrees of Spurious Correlations},
    booktitle = {International Conference in Computer Analysis of Images and Patterns (CAIP)},
    year = {2025},
    pages = {},
    abstract = {Deep neural networks are prone to shortcut bias,where models rely on features that are statistically associated with the target label but lack causal relevance, leading to poor generalization under distribution shifts. To add ress this, debiasing methods aim to improve robustness by reducing reliance on these spurious features. Unfortunately, existing approaches typically assume unbiased test distributions, an idealized scenario that rarely holds in practice. As a result, they often underperform on the original biased distribution when compared with standard empirical risk minimization (ERM) models. We propose a novel Adaptive Model SELection approach for expanding post hoc debiasing called AMSEL, which maintains strong performance across test distributions with varying strength of spurious correlation. Using the fixed feature extractor of the biased model, AMSEL trains a family of lightweight classifier heads on simulated distributions ranging from the original biased data to a fully balanced version. At test time, it estimates the degree of spurious correlation in the test data and selects the most suitable classifier. We validate AMSEL on CelebA and ChestX-ray14, demonstrating that it matches the performance of debiased models under unbiased conditions while preserving the accuracy of the original biased model when spurious correlations are prevalent. AMSEL thus offers an adaptive solution to mitigate the impact of spurious correlations when their strength is either unknown or varies across application environments. Code and models are publicly available at https://github.com/debiasing/AMSEL.},
    doi = {},
    url = {https://blunk.sh/blunk2025amsel.pdf},
    groups = {understanding-dl,adaptivelearning},
    note = {(accepted)},
}