ArticleIEEE Winter Conference on Applications of Computer Vision. IEEE Winter Conference on Applications of Computer Vision2021
Representation Learning with Statistical Independence to Mitigate Bias.
Article in IEEE Winter Conference on Applications of Computer Vision. IEEE Winter Conference on Applications of Computer Vision, 2021. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 23 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
23 citing papers in PubMed.
- Deceptive bias measurement in deep learning: Assessing shortcut reliance in TCGA cancer models.PLOS digital health · 2026Article
- Strategies for mitigating artificial intelligence bias in healthcare: a systematic review.JAMIA open · 2026Review
- Artificial intelligence improves detection and classification of pulmonary venous hypertension related to left ventricular diastolic dysfunction by chest radiography.Scientific reports · 2025Article
- Ethical considerations and robustness of artificial neural networks in medical image analysis under data corruption.Scientific reports · 2025Article
- Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects.Diagnostic and interventional radiology (Ankara, Turkey) · 2025Review
- A Method for Multimodal IVA Fusion Within a MISA Unified Model Reveals Markers of Age, Sex, Cognition, and Schizophrenia in Large Neuroimaging Studies.Human brain mapping · 2024Article
- Towards objective and systematic evaluation of bias in artificial intelligence for medical imaging.Journal of the American Medical Informatics Association : JAMIA · 2024Article
- Addressing fairness issues in deep learning-based medical image analysis: a systematic review.NPJ digital medicine · 2024Review
- Novel multi-omics deconfounding variational autoencoders can obtain meaningful disease subtyping.Briefings in bioinformatics · 2024Article
- Metadata-guided feature disentanglement for functional genomics.Bioinformatics (Oxford, England) · 2024Article
- Drop the shortcuts: image augmentation improves fairness and decreases AI detection of race and other demographics from medical images.EBioMedicine · 2024Article
- Efficient adversarial debiasing with concept activation vector - Medical image case-studies.Journal of biomedical informatics · 2024Article
- Subject Harmonization of Digital Biomarkers: Improved Detection of Mild Cognitive Impairment from Language Markers.Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing · 2024Article
- HACA3: A unified approach for multi-site MR image harmonization.Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society · 2023Article
- Mitigating Racial And Ethnic Bias And Advancing Health Equity In Clinical Algorithms: A Scoping Review.Health affairs (Project Hope) · 2023Article
- Deep learning identifies morphological patterns of homologous recombination deficiency in luminal breast cancers from whole slide images.Cell reports. Medicine · 2022Article
- Article
- Multi-label, multi-domain learning identifies compounding effects of HIV and cognitive impairment.Medical image analysis · 2022Article
- Automated eloquent cortex localization in brain tumor patients using multi-task graph neural networks.Medical image analysis · 2021Article
- Metadata Normalization.Proceedings. IEEE Computer Society Conference on Computer Vision and Pattern Recognition · 2021Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
7 authors.
Funding
Abstract
Presence of bias (in datasets or tasks) is inarguably one of the most critical challenges in machine learning applications that has alluded to pivotal debates in recent years. Such challenges range from spurious associations between variables in medical studies to the bias of race in gender or face recognition systems. Controlling for all types of biases in the dataset curation stage is cumbersome and sometimes impossible. The alternative is to use the available data and build models incorporating fair representation learning. In this paper, we propose such a model based on adversarial training with two competing objectives to learn features that have (1) maximum discriminative power with respect to the task and (2) minimal statistical mean dependence with the protected (bias) variable(s). Our approach does so by incorporating a new adversarial loss function that encourages a vanished correlation between the bias and the learned features. We apply our method to synthetic data, medical images (containing task bias), and a dataset for gender classification (containing dataset bias). Our results show that the learned features by our method not only result in superior prediction performance but also are unbiased.
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.