Test Time Adaptation for Blind Image Quality Assessment

TL;DR

This paper proposes test time adaptation techniques for blind image quality assessment by introducing novel auxiliary tasks and loss functions, enabling models to adapt to new data distributions and improve performance during inference.

Contribution

It introduces two novel quality-relevant auxiliary tasks and loss functions for test time adaptation in blind IQA, focusing on batch and sample level adaptation.

Findings

Significant performance improvements with small test batches.

Updating batch normalization statistics enhances model adaptation.

Proposed methods outperform baseline without additional training.

Abstract

While the design of blind image quality assessment (IQA) algorithms has improved significantly, the distribution shift between the training and testing scenarios often leads to a poor performance of these methods at inference time. This motivates the study of test time adaptation (TTA) techniques to improve their performance at inference time. Existing auxiliary tasks and loss functions used for TTA may not be relevant for quality-aware adaptation of the pre-trained model. In this work, we introduce two novel quality-relevant auxiliary tasks at the batch and sample levels to enable TTA for blind IQA. In particular, we introduce a group contrastive loss at the batch level and a relative rank loss at the sample level to make the model quality aware and adapt to the target data. Our experiments reveal that even using a small batch of images from the test distribution helps achieve significant improvement in performance by updating the batch normalization statistics of the source model.