# Deep Active Learning with Contrastive Learning Under Realistic Data Pool Assumptions

arXiv: https://arxiv.org/abs/2303.14433 · HTML: https://mlsanity.com/paper/2303.14433/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 14 references that are in the map.
- First posted on arXiv 25 Mar 2023.

## Builds on (most cited first, 11 of 11)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [NVAE: A Deep Hierarchical Variational Autoencoder](https://mlsanity.com/paper/2007.03898/) (2020)
- [CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances](https://mlsanity.com/paper/2007.08176/) (2020)
- [BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning](https://mlsanity.com/paper/1906.08158/) (2019)
- [Variational Adversarial Active Learning](https://mlsanity.com/paper/1904.00370/) (2019)
- [SIMILAR: Submodular Information Measures Based Active Learning In Realistic Scenarios](https://mlsanity.com/paper/2107.00717/) (2021)
- [Active Learning for Open-set Annotation](https://mlsanity.com/paper/2201.06758/) (2022)
- [A Unified Benchmark for the Unknown Detection Capability of Deep Neural Networks](https://mlsanity.com/paper/2112.00337/) (2021)
- [Deep Active Learning via Open Set Recognition](https://mlsanity.com/paper/2007.02196/) (2020)

## Built on by (most cited first, 3 of 3)

- [Integrating Deep Metric Learning with Coreset for Active Learning in 3D Segmentation](https://mlsanity.com/paper/2411.15763/) (2024)
- [Active Learning with Task-Driven Representations for Messy Pools](https://mlsanity.com/paper/2510.25926/) (2025)
- [FIDAL: Diversity-Aware Federated Active Learning Under Real-World Distribution Shifts](https://mlsanity.com/paper/2609.31637/) (2026)

## Abstract (arXiv)

Active learning aims to identify the most informative data from an unlabeled data pool that enables a model to reach the desired accuracy rapidly. This benefits especially deep neural networks which generally require a huge number of labeled samples to achieve high performance. Most existing active learning methods have been evaluated in an ideal setting where only samples relevant to the target task, i.e., in-distribution samples, exist in an unlabeled data pool. A data pool gathered from the wild, however, is likely to include samples that are irrelevant to the target task at all and/or too ambiguous to assign a single class label even for the oracle. We argue that assuming an unlabeled data pool consisting of samples from various distributions is more realistic. In this work, we introduce new active learning benchmarks that include ambiguous, task-irrelevant out-of-distribution as well as in-distribution samples. We also propose an active learning method designed to acquire informative in-distribution samples in priority. The proposed method leverages both labeled and unlabeled data pools and selects samples from clusters on the feature space constructed via contrastive learning. Experimental results demonstrate that the proposed method requires a lower annotation budget than existing active learning methods to reach the same level of accuracy.