# On Deep Unsupervised Active Learning

arXiv: https://arxiv.org/abs/2007.13959 · HTML: https://mlsanity.com/paper/2007.13959/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Jul 2020.

## Built on by (most cited first, 10 of 10)

- [A Survey on Deep Active Learning: Recent Advances and New Frontiers](https://mlsanity.com/paper/2405.00334/) (2024)
- [Improving Semi-Supervised and Domain-Adaptive Semantic Segmentation with Self-Supervised Depth Estimation](https://mlsanity.com/paper/2108.12545/) (2021)
- [Self-Supervised Information Bottleneck for Deep Multi-View Subspace Clustering](https://mlsanity.com/paper/2204.12496/) (2022)
- [Empowering Language Models with Active Inquiry for Deeper Understanding](https://mlsanity.com/paper/2402.03719/) (2024)
- [MEAL: Manifold Embedding-based Active Learning](https://mlsanity.com/paper/2106.11858/) (2021)
- [Deep Unsupervised Active Learning on Learnable Graphs](https://mlsanity.com/paper/2111.04286/) (2021)
- [Is Policy Learning Overrated?: Width-Based Planning and Active Learning for Atari](https://mlsanity.com/paper/2109.15310/) (2021)
- [Unsupervised Clustering Active Learning for Person Re-identification](https://mlsanity.com/paper/2112.13308/) (2021)
- [Unsupervised Active Learning via Natural Feature Progressive Framework](https://mlsanity.com/paper/2510.04939/) (2025)
- [Goal-Oriented Influence-Maximizing Data Acquisition for Learning and Optimization](https://mlsanity.com/paper/2602.19578/) (2026)

## Abstract (arXiv)

Unsupervised active learning has attracted increasing attention in recent years, where its goal is to select representative samples in an unsupervised setting for human annotating. Most existing works are based on shallow linear models by assuming that each sample can be well approximated by the span (i.e., the set of all linear combinations) of certain selected samples, and then take these selected samples as representative ones to label. However, in practice, the data do not necessarily conform to linear models, and how to model nonlinearity of data often becomes the key point to success. In this paper, we present a novel Deep neural network framework for Unsupervised Active Learning, called DUAL. DUAL can explicitly learn a nonlinear embedding to map each input into a latent space through an encoder-decoder architecture, and introduce a selection block to select representative samples in the the learnt latent space. In the selection block, DUAL considers to simultaneously preserve the whole input patterns as well as the cluster structure of data. Extensive experiments are performed on six publicly available datasets, and experimental results clearly demonstrate the efficacy of our method, compared with state-of-the-arts.