# Deep Active Learning via Open Set Recognition

arXiv: https://arxiv.org/abs/2007.02196 · HTML: https://mlsanity.com/paper/2007.02196/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Jul 2020.

## Built on by (most cited first, 5 of 5)

- [Managing the unknown: a survey on Open Set Recognition and tangential areas](https://mlsanity.com/paper/2312.08785/) (2023)
- [Deep Active Learning with Contrastive Learning Under Realistic Data Pool Assumptions](https://mlsanity.com/paper/2303.14433/) (2023)
- [Domain Agnostic Few-Shot Learning For Document Intelligence](https://mlsanity.com/paper/2111.00007/) (2021)
- [Deep Active Learning Using Barlow Twins](https://mlsanity.com/paper/2212.14658/) (2022)
- [Interactive Event Sifting using Bayesian Graph Neural Networks](https://mlsanity.com/paper/2410.05359/) (2024)

## Abstract (arXiv)

In many applications, data is easy to acquire but expensive and time-consuming to label prominent examples include medical imaging and NLP. This disparity has only grown in recent years as our ability to collect data improves. Under these constraints, it makes sense to select only the most informative instances from the unlabeled pool and request an oracle (e.g., a human expert) to provide labels for those samples. The goal of active learning is to infer the informativeness of unlabeled samples so as to minimize the number of requests to the oracle. Here, we formulate active learning as an open-set recognition problem. In this paradigm, only some of the inputs belong to known classes; the classifier must identify the rest as unknown. More specifically, we leverage variational neural networks (VNNs), which produce high-confidence (i.e., low-entropy) predictions only for inputs that closely resemble the training data. We use the inverse of this confidence measure to select the samples that the oracle should label. Intuitively, unlabeled samples that the VNN is uncertain about are more informative for future training. We carried out an extensive evaluation of our novel, probabilistic formulation of active learning, achieving state-of-the-art results on MNIST, CIFAR-10, and CIFAR-100. Additionally, unlike current active learning methods, our algorithm can learn tasks without the need for task labels. As our experiments show, when the unlabeled pool consists of a mixture of samples from multiple datasets, our approach can automatically distinguish between samples from seen vs. unseen tasks.