While recent advancements in large multimodal models (LMMs) have significantly improved their abilities in image quality assessment (IQA) relying on absolute quality rating, how to transfer reliable relative quality comparison outputs to continuous perceptual quality scores remains largely unexplored.

We also show that MatrixNet respects group relations allowing generalization to group elements of greater word length than in the training set.

When such outliers occur at the end of the data stream, this can cause the final solution to have unexpectedly low accuracy.

Machine learning models are famously vulnerable to adversarial attacks: small ad-hoc perturbations of the data that can catastrophically alter the model predictions.