# Semi-supervised Ranking for Object Image Blur Assessment

arXiv: https://arxiv.org/abs/2207.06085 · HTML: https://mlsanity.com/paper/2207.06085/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 22 references that are in the map.
- First posted on arXiv 13 Jul 2022.

## Builds on (most cited first, 13 of 13)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Learning Face Representation from Scratch](https://mlsanity.com/paper/1411.7923/) (2014)
- [NIMA: Neural Image Assessment](https://mlsanity.com/paper/1709.05424/) (2017)
- [MagFace: A Universal Representation for Face Recognition and Quality Assessment](https://mlsanity.com/paper/2103.06627/) (2021)
- [WIDER FACE: A Face Detection Benchmark](https://mlsanity.com/paper/1511.06523/) (2015)
- [The MegaFace Benchmark: 1 Million Faces for Recognition at Scale](https://mlsanity.com/paper/1512.00596/) (2015)
- [RankIQA: Learning from Rankings for No-reference Image Quality Assessment](https://mlsanity.com/paper/1707.08347/) (2017)
- [dipIQ: Blind Image Quality Assessment by Learning-to-Rank Discriminable Image Pairs](https://mlsanity.com/paper/1904.06505/) (2019)
- [Vehicle Re-identification in Aerial Imagery: Dataset and Approach](https://mlsanity.com/paper/1904.01400/) (2019)
- [LPRNet: License Plate Recognition via Deep Neural Networks](https://mlsanity.com/paper/1806.10447/) (2018)
- [EQFace: A Simple Explicit Quality Network for Face Recognition](https://mlsanity.com/paper/2105.00634/) (2021)
- [Object-QA: Towards High Reliable Object Quality Assessment](https://mlsanity.com/paper/2005.13116/) (2020)

## Abstract (arXiv)

Assessing the blurriness of an object image is fundamentally important to improve the performance for object recognition and retrieval. The main challenge lies in the lack of abundant images with reliable labels and effective learning strategies. Current datasets are labeled with limited and confused quality levels. To overcome this limitation, we propose to label the rank relationships between pairwise images rather their quality levels, since it is much easier for humans to label, and establish a large-scale realistic face image blur assessment dataset with reliable labels. Based on this dataset, we propose a method to obtain the blur scores only with the pairwise rank labels as supervision. Moreover, to further improve the performance, we propose a self-supervised method based on quadruplet ranking consistency to leverage the unlabeled data more effectively. The supervised and self-supervised methods constitute a final semi-supervised learning framework, which can be trained end-to-end. Experimental results demonstrate the effectiveness of our method.