We propose a novel approach to mitigate biases in computer vision models by utilizing counterfactual generation and fine-tuning. While counterfactuals have been used to analyze and address biases in DNN models, the counterfactuals themselves are often generated from biased generative models, which can introduce additional biases or spurious correlations. To address this issue, we propose using adversarial images, that is images that deceive a deep neural network but not humans, as counterfactuals for fair model training. Our approach leverages a curriculum learning framework combined with a fine-grained adversarial loss to fine-tune the model using adversarial examples. By incorporating adversarial images into the training data, we aim to prevent biases from propagating through the pipeline. We validate our approach through both qualitative and quantitative assessments, demonstrating improved bias mitigation and accuracy compared to existing methods. Qualitatively, our results indicate that post-training, the decisions made by the model are less dependent on the sensitive attribute and our model better disentangles the relationship between sensitive attributes and classification variables.
Blindness and other eye diseases are a global health concern, particularly in low- and middle-income countries like India. In this regard, during the COVID-19 pandemic, teleophthalmology became a lifeline, and the Grabi attachment for smartphone-based eye imaging gained in use. However, quality of user-captured image often remained inadequate, requiring clinician vetting and delays. In this backdrop, we propose an AI-based quality assessment system with instant feedback mimicking clinicians' judgments and tested on patient-captured images. Dividing the complex problem hierarchically, here we tackle a nontrivial part, and demonstrate a proof of the concept.