# Semi-Supervised Variational Adversarial Active Learning via Learning to Rank and Agreement-Based Pseudo Labeling

arXiv: https://arxiv.org/abs/2408.12774 · HTML: https://mlsanity.com/paper/2408.12774/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 40 references that are in the map.
- First posted on arXiv 23 Aug 2024.

## Builds on (most cited first, 17 of 17)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Deep Bayesian Active Learning with Image Data](https://mlsanity.com/paper/1703.02910/) (2017)
- [Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds](https://mlsanity.com/paper/1906.03671/) (2019)
- [Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning](https://mlsanity.com/paper/1908.02983/) (2019)
- [Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learning](https://mlsanity.com/paper/1606.04586/) (2016)
- [Learning Loss for Active Learning](https://mlsanity.com/paper/1905.03677/) (2019)
- [In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning](https://mlsanity.com/paper/2101.06329/) (2021)
- [Dilated Residual Networks](https://mlsanity.com/paper/1705.09914/) (2017)
- [Variational Adversarial Active Learning](https://mlsanity.com/paper/1904.00370/) (2019)
- [Cost-Effective Active Learning for Deep Image Classification](https://mlsanity.com/paper/1701.03551/) (2017)
- [Task-Aware Variational Adversarial Active Learning](https://mlsanity.com/paper/2002.04709/) (2020)
- [Rethinking deep active learning: Using unlabeled data at model training](https://mlsanity.com/paper/1911.08177/) (2019)
- [SoDeep: a Sorting Deep net to learn ranking loss surrogates](https://mlsanity.com/paper/1904.04272/) (2019)
- [Learning to Rank for Active Learning: A Listwise Approach](https://mlsanity.com/paper/2008.00078/) (2020)
- [Ranking CGANs: Subjective Control over Semantic Image Attributes](https://mlsanity.com/paper/1804.04082/) (2018)
- [Exploiting Diversity of Unlabeled Data for Label-Efficient Semi-Supervised Active Learning](https://mlsanity.com/paper/2207.12302/) (2022)

## Built on by (most cited first, 2 of 2)

- [Diffusion-Driven Two-Stage Active Learning for Low-Budget Semantic Segmentation](https://mlsanity.com/paper/2510.22229/) (2025)
- [Energy-Based Open-Set Active Learning for Object Classification](https://mlsanity.com/paper/2604.20083/) (2026)

## Abstract (arXiv)

Active learning aims to alleviate the amount of labor involved in data labeling by automating the selection of unlabeled samples via an acquisition function. For example, variational adversarial active learning (VAAL) leverages an adversarial network to discriminate unlabeled samples from labeled ones using latent space information. However, VAAL has the following shortcomings: (i) it does not exploit target task information, and (ii) unlabeled data is only used for sample selection rather than model training. To address these limitations, we introduce novel techniques that significantly improve the use of abundant unlabeled data during training and take into account the task information. Concretely, we propose an improved pseudo-labeling algorithm that leverages information from all unlabeled data in a semi-supervised manner, thus allowing a model to explore a richer data space. In addition, we develop a ranking-based loss prediction module that converts predicted relative ranking information into a differentiable ranking loss. This loss can be embedded as a rank variable into the latent space of a variational autoencoder and then trained with a discriminator in an adversarial fashion for sample selection. We demonstrate the superior performance of our approach over the state of the art on various image classification and segmentation benchmark datasets.