# Less is More: Learning Reference Knowledge Using No-Reference Image Quality Assessment

arXiv: https://arxiv.org/abs/2312.00591 · HTML: https://mlsanity.com/paper/2312.00591/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 66 references that are in the map.
- First posted on arXiv 1 Dec 2023.

## Builds on (most cited first, 8 of 8)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [DeiT III: Revenge of the ViT](https://mlsanity.com/paper/2204.07118/) (2022)
- [Knowledge Distillation by On-the-Fly Native Ensemble](https://mlsanity.com/paper/1806.04606/) (2018)
- [Quality-aware Pre-trained Models for Blind Image Quality Assessment](https://mlsanity.com/paper/2303.00521/) (2023)
- [Content-Variant Reference Image Quality Assessment via Knowledge Distillation](https://mlsanity.com/paper/2202.13123/) (2022)

## Abstract (arXiv)

Image Quality Assessment (IQA) with reference images have achieved great success by imitating the human vision system, in which the image quality is effectively assessed by comparing the query image with its pristine reference image. However, for the images in the wild, it is quite difficult to access accurate reference images. We argue that it is possible to learn reference knowledge under the No-Reference Image Quality Assessment (NR-IQA) setting, which is effective and efficient empirically. Concretely, by innovatively introducing a novel feature distillation method in IQA, we propose a new framework to learn comparative knowledge from non-aligned reference images. And then, to achieve fast convergence and avoid overfitting, we further propose an inductive bias regularization. Such a framework not only solves the congenital defects of NR-IQA but also improves the feature extraction framework, enabling it to express more abundant quality information. Surprisingly, our method utilizes less input while obtaining a more significant improvement compared to the teacher models. Extensive experiments on eight standard NR-IQA datasets demonstrate the superior performance to the state-of-the-art NR-IQA methods, i.e., achieving the PLCC values of 0.917 (vs. 0.884 in LIVEC) and 0.686 (vs. 0.661 in LIVEFB).