Beyond Classification: Task-Dependent Learnability under Privacy-Motivated Image Transformations
Privacy-Enhancing Technologies (PETs) in computer vision often rely on noise or image perturbations to protect visual data while securely processing it, creating a trade-off between task performance and protection. This trade-off is commonly evaluated using image classification, which primarily captures semantic separability and remains robust despite significant geometric, spatial layout or…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
