# Exploiting Unlabeled Data in CNNs by Self-supervised Learning to Rank

arXiv: https://arxiv.org/abs/1902.06285 · HTML: https://mlsanity.com/paper/1902.06285/

## Key facts

- Cited by 52 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Feb 2019.

## Built on by (most cited first, 30 of 52)

- [Image Quality Assessment using Contrastive Learning](https://mlsanity.com/paper/2110.13266/) (2021)
- [Domain Enhanced Arbitrary Image Style Transfer via Contrastive Learning](https://mlsanity.com/paper/2205.09542/) (2022)
- [Towards Open-ended Visual Quality Comparison](https://mlsanity.com/paper/2402.16641/) (2024)
- [TransCrowd: weakly-supervised crowd counting with transformers](https://mlsanity.com/paper/2104.09116/) (2021)
- [Neighbourhood Representative Sampling for Efficient End-to-end Video Quality Assessment](https://mlsanity.com/paper/2210.05357/) (2022)
- [CrowdCLIP: Unsupervised Crowd Counting via Vision-Language Model](https://mlsanity.com/paper/2304.04231/) (2023)
- [Towards Explainable In-the-Wild Video Quality Assessment: A Database and a Language-Prompted Approach](https://mlsanity.com/paper/2305.12726/) (2023)
- [Reducing Label Effort: Self-Supervised meets Active Learning](https://mlsanity.com/paper/2108.11458/) (2021)
- [Self-supervised Contrastive Representation Learning for Semi-supervised Time-Series Classification](https://mlsanity.com/paper/2208.06616/) (2022)
- [Spatial Uncertainty-Aware Semi-Supervised Crowd Counting](https://mlsanity.com/paper/2107.13271/) (2021)
- [CCTrans: Simplifying and Improving Crowd Counting with Transformer](https://mlsanity.com/paper/2109.14483/) (2021)
- [Cross-View Cross-Scene Multi-View Crowd Counting](https://mlsanity.com/paper/2205.01551/) (2022)
- [Leveraging Self-Supervision for Cross-Domain Crowd Counting](https://mlsanity.com/paper/2103.16291/) (2021)
- [Calibrating Uncertainty for Semi-Supervised Crowd Counting](https://mlsanity.com/paper/2308.09887/) (2023)
- [Semi-supervised Crowd Counting via Density Agency](https://mlsanity.com/paper/2209.02955/) (2022)
- [Redesigning Multi-Scale Neural Network for Crowd Counting](https://mlsanity.com/paper/2208.02894/) (2022)
- [Data Scarcity in Recommendation Systems: A Survey](https://mlsanity.com/paper/2312.10073/) (2023)
- [Revisiting Crowd Counting: State-of-the-art, Trends, and Future Perspectives](https://mlsanity.com/paper/2209.07271/) (2022)
- [A strong baseline for image and video quality assessment](https://mlsanity.com/paper/2111.07104/) (2021)
- [A Unified Arbitrary Style Transfer Framework via Adaptive Contrastive Learning](https://mlsanity.com/paper/2303.12710/) (2023)
- [RGB-D Indiscernible Object Counting in Underwater Scenes](https://mlsanity.com/paper/2304.11677/) (2023)
- [Transformer-based No-Reference Image Quality Assessment via Supervised Contrastive Learning](https://mlsanity.com/paper/2312.06995/) (2023)
- [Rethinking Global Context in Crowd Counting](https://mlsanity.com/paper/2105.10926/) (2021)
- [CrowdFormer: Weakly-supervised Crowd counting with Improved Generalizability](https://mlsanity.com/paper/2203.03768/) (2022)
- [On the Effectiveness of Spectral Discriminators for Perceptual Quality Improvement](https://mlsanity.com/paper/2307.12027/) (2023)
- [Contrastive Learning for Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/2105.03117/) (2021)
- [A Low Rank Promoting Prior for Unsupervised Contrastive Learning](https://mlsanity.com/paper/2108.02696/) (2021)
- [Semi-supervised Counting via Pixel-by-pixel Density Distribution Modelling](https://mlsanity.com/paper/2402.15297/) (2024)
- [Set-to-Sequence Methods in Machine Learning: a Review](https://mlsanity.com/paper/2103.09656/) (2021)
- [TreeFormer: a Semi-Supervised Transformer-based Framework for Tree Counting from a Single High Resolution Image](https://mlsanity.com/paper/2307.06118/) (2023)

## Abstract (arXiv)

For many applications the collection of labeled data is expensive laborious. Exploitation of unlabeled data during training is thus a long pursued objective of machine learning. Self-supervised learning addresses this by positing an auxiliary task (different, but related to the supervised task) for which data is abundantly available. In this paper, we show how ranking can be used as a proxy task for some regression problems. As another contribution, we propose an efficient backpropagation technique for Siamese networks which prevents the redundant computation introduced by the multi-branch network architecture. We apply our framework to two regression problems: Image Quality Assessment (IQA) and Crowd Counting. For both we show how to automatically generate ranked image sets from unlabeled data. Our results show that networks trained to regress to the ground truth targets for labeled data and to simultaneously learn to rank unlabeled data obtain significantly better, state-of-the-art results for both IQA and crowd counting. In addition, we show that measuring network uncertainty on the self-supervised proxy task is a good measure of informativeness of unlabeled data. This can be used to drive an algorithm for active learning and we show that this reduces labeling effort by up to 50%.