STAPLE: Siamese Transformer Assisted Pseudo Label Ensembling for Unsupervised Domain Adaptation in No-Reference IQA

Traditional Image Quality Assessment models rely on image - Mean Opinion Scores pairs from a specific source domain to train a robust mapping function in a fully supervised manner. While these methods excel on test images with distortions similar to the training data, their effectiveness drops sharply when tested on novel distortions, necessitating expensive fine-tuning with additional annotations and hyper-parameter optimization. To address these challenges, we present Siamese Transformer Assisted Pseudo Label Ensembling (STAPLE), a novel Unsupervised Domain Adaptation (UDA) technique for No-Reference IQA. STAPLE leverages a Siamese Transformer Network that learns quality differences between image pairs and generates high-quality pseudo-labels by pairing unlabeled target images with labeled source images. By ensembling predictions from multiple source references, our method robustly reduces variance and consistently maintains high accuracy on both source and target domains. Notably, STAPLE excels in cross-distortion adaptation within a synthetic dataset, even with zero overlap between source and target distributions. Extensive experiments across multiple scenarios, including synthetic-to-in-the-wild and vice versa, demonstrate its effectiveness in challenging real-world conditions.