# PT4AL: Using Self-Supervised Pretext Tasks for Active Learning

arXiv: https://arxiv.org/abs/2201.07459 · HTML: https://mlsanity.com/paper/2201.07459/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 55 references that are in the map.
- First posted on arXiv 19 Jan 2022.

## Builds on (most cited first, 29 of 29)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [Unsupervised Representation Learning by Predicting Image Rotations](https://mlsanity.com/paper/1803.07728/) (2018)
- [Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles](https://mlsanity.com/paper/1603.09246/) (2016)
- [Graph Contrastive Learning with Augmentations](https://mlsanity.com/paper/2010.13902/) (2020)
- [Colorful Image Colorization](https://mlsanity.com/paper/1603.08511/) (2016)
- [Unsupervised Visual Representation Learning by Context Prediction](https://mlsanity.com/paper/1505.05192/) (2015)
- [Do Better ImageNet Models Transfer Better?](https://mlsanity.com/paper/1805.08974/) (2018)
- [Learning Loss for Active Learning](https://mlsanity.com/paper/1905.03677/) (2019)
- [Variational Adversarial Active Learning](https://mlsanity.com/paper/1904.00370/) (2019)
- [When Do Curricula Work?](https://mlsanity.com/paper/2012.03107/) (2020)
- [Task-Aware Variational Adversarial Active Learning](https://mlsanity.com/paper/2002.04709/) (2020)
- [Influence Selection for Active Learning](https://mlsanity.com/paper/2108.09331/) (2021)
- [Sequential Graph Convolutional Network for Active Learning](https://mlsanity.com/paper/2006.10219/) (2020)
- [Semantic Redundancies in Image-Classification Datasets: The 10% You Don't Need](https://mlsanity.com/paper/1901.11409/) (2019)
- [Reducing Label Effort: Self-Supervised meets Active Learning](https://mlsanity.com/paper/2108.11458/) (2021)
- [Are Labels Necessary for Neural Architecture Search?](https://mlsanity.com/paper/2003.12056/) (2020)
- [MCDAL: Maximum Classifier Discrepancy for Active Learning](https://mlsanity.com/paper/2107.11049/) (2021)
- [A Simple Baseline for Low-Budget Active Learning](https://mlsanity.com/paper/2110.12033/) (2021)
- [A Variance Maximization Criterion for Active Learning](https://mlsanity.com/paper/1706.07642/) (2017)
- [PAL : Pretext-based Active Learning](https://mlsanity.com/paper/2010.15947/) (2020)

## Built on by (most cited first, 27 of 27)

- [Plex: Towards Reliability using Pretrained Large Model Extensions](https://mlsanity.com/paper/2207.07411/) (2022)
- [Active Finetuning: Exploiting Annotation Budget in the Pretraining-Finetuning Paradigm](https://mlsanity.com/paper/2303.14382/) (2023)
- [A comprehensive survey on deep active learning in medical image analysis](https://mlsanity.com/paper/2310.14230/) (2023)
- [Navigating the Pitfalls of Active Learning Evaluation: A Systematic Framework for Meaningful Performance Assessment](https://mlsanity.com/paper/2301.10625/) (2023)
- [ActiveAD: Planning-Oriented Active Learning for End-to-End Autonomous Driving](https://mlsanity.com/paper/2403.02877/) (2024)
- [ActiveGLAE: A Benchmark for Deep Active Learning with Transformers](https://mlsanity.com/paper/2306.10087/) (2023)
- [Towards Free Data Selection with General-Purpose Models](https://mlsanity.com/paper/2309.17342/) (2023)
- [Making Better Use of Unlabelled Data in Bayesian Active Learning](https://mlsanity.com/paper/2404.17249/) (2024)
- [BAL: Balancing Diversity and Novelty for Active Learning](https://mlsanity.com/paper/2312.15944/) (2023)
- [Bidirectional Domain Mixup for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2303.09779/) (2023)
- [A Unified Approach Towards Active Learning and Out-of-Distribution Detection](https://mlsanity.com/paper/2405.11337/) (2024)
- [Deep Active Learning in the Presence of Label Noise: A Survey](https://mlsanity.com/paper/2302.11075/) (2023)
- [Bayesian Active Learning for Semantic Segmentation](https://mlsanity.com/paper/2408.01694/) (2024)
- [Beyond Labeling Oracles: What does it mean to steal ML models?](https://mlsanity.com/paper/2310.01959/) (2023)
- [Downstream-Pretext Domain Knowledge Traceback for Active Learning](https://mlsanity.com/paper/2407.14720/) (2024)
- [A Pre-trained Data Deduplication Model based on Active Learning](https://mlsanity.com/paper/2308.00721/) (2023)
- [How To Overcome Confirmation Bias in Semi-Supervised Image Classification By Active Learning](https://mlsanity.com/paper/2308.08224/) (2023)
- [Compute-Efficient Active Learning](https://mlsanity.com/paper/2401.07639/) (2024)
- [MV-MR: multi-views and multi-representations for self-supervised learning and knowledge distillation](https://mlsanity.com/paper/2303.12130/) (2023)
- [Cold PAWS: Unsupervised class discovery and addressing the cold-start problem for semi-supervised learning](https://mlsanity.com/paper/2305.10071/) (2023)
- [Enhancing Modality Representation and Alignment for Multimodal Cold-start Active Learning](https://mlsanity.com/paper/2412.09126/) (2024)
- [Efficient Human-in-the-Loop Active Learning: A Novel Framework for Data Labeling in AI Systems](https://mlsanity.com/paper/2501.00277/) (2024)
- [Using Sum-Product Networks to Assess Uncertainty in Deep Active Learning](https://mlsanity.com/paper/2206.09798/) (2022)
- [1st Place Solution to NeurIPS 2022 Challenge on Visual Domain Adaptation](https://mlsanity.com/paper/2211.14596/) (2022)
- [Critic Loss for Image Classification](https://mlsanity.com/paper/2409.15565/) (2024)
- [A3: Active Adversarial Alignment for Source-Free Domain Adaptation](https://mlsanity.com/paper/2409.18418/) (2024)
- [Unsupervised Active Learning via Natural Feature Progressive Framework](https://mlsanity.com/paper/2510.04939/) (2025)

## Abstract (arXiv)

Labeling a large set of data is expensive. Active learning aims to tackle this problem by asking to annotate only the most informative data from the unlabeled set. We propose a novel active learning approach that utilizes self-supervised pretext tasks and a unique data sampler to select data that are both difficult and representative. We discover that the loss of a simple self-supervised pretext task, such as rotation prediction, is closely correlated to the downstream task loss. Before the active learning iterations, the pretext task learner is trained on the unlabeled set, and the unlabeled data are sorted and split into batches by their pretext task losses. In each active learning iteration, the main task model is used to sample the most uncertain data in a batch to be annotated. We evaluate our method on various image classification and segmentation benchmarks and achieve compelling performances on CIFAR10, Caltech-101, ImageNet, and Cityscapes. We further show that our method performs well on imbalanced datasets, and can be an effective solution to the cold-start problem where active learning performance is affected by the randomly sampled initial labeled set.