# Active and Continuous Exploration with Deep Neural Networks and Expected Model Output Changes

arXiv: https://arxiv.org/abs/1612.06129 · HTML: https://mlsanity.com/paper/1612.06129/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Dec 2016.

## Built on by (most cited first, 18 of 18)

- [Multiple instance active learning for object detection](https://mlsanity.com/paper/2104.02324/) (2021)
- [Semi-Supervised Active Learning with Temporal Output Discrepancy](https://mlsanity.com/paper/2107.14153/) (2021)
- [Making Look-Ahead Active Learning Strategies Feasible with Neural Tangent Kernels](https://mlsanity.com/paper/2206.12569/) (2022)
- [Generalized Coverage for More Robust Low-Budget Active Learning](https://mlsanity.com/paper/2407.12212/) (2024)
- [Uncertainty Herding: One Active Learning Method for All Label Budgets](https://mlsanity.com/paper/2412.20644/) (2024)
- [Deep Active Learning for Computer Vision: Past and Future](https://mlsanity.com/paper/2211.14819/) (2022)
- [Downstream-Pretext Domain Knowledge Traceback for Active Learning](https://mlsanity.com/paper/2407.14720/) (2024)
- [Temporal Output Discrepancy for Loss Estimation-based Active Learning](https://mlsanity.com/paper/2212.10613/) (2022)
- [Pruning-based Data Selection and Network Fusion for Efficient Deep Learning](https://mlsanity.com/paper/2501.01118/) (2025)
- [Can I see an Example? Active Learning the Long Tail of Attributes and Relations](https://mlsanity.com/paper/2203.06215/) (2022)
- [Does Deep Active Learning Work in the Wild?](https://mlsanity.com/paper/2302.00098/) (2023)
- [Classification Committee for Active Deep Object Detection](https://mlsanity.com/paper/2308.08476/) (2023)
- [Two-Step Active Learning for Instance Segmentation with Uncertainty and Diversity Sampling](https://mlsanity.com/paper/2309.16139/) (2023)
- [Exploring Active Learning in Meta-Learning: Enhancing Context Set Labeling](https://mlsanity.com/paper/2311.02879/) (2023)
- [Domain Adaptation and Active Learning for Fine-Grained Recognition in the Field of Biodiversity](https://mlsanity.com/paper/2110.11778/) (2021)
- [Critic Loss for Image Classification](https://mlsanity.com/paper/2409.15565/) (2024)
- [Diffusion-Driven Two-Stage Active Learning for Low-Budget Semantic Segmentation](https://mlsanity.com/paper/2510.22229/) (2025)
- [PruneFuse: Efficient Data Selection via Weight Pruning and Network Fusion](https://mlsanity.com/paper/2603.26138/) (2026)

## Abstract (arXiv)

The demands on visual recognition systems do not end with the complexity offered by current large-scale image datasets, such as ImageNet. In consequence, we need curious and continuously learning algorithms that actively acquire knowledge about semantic concepts which are present in available unlabeled data. As a step towards this goal, we show how to perform continuous active learning and exploration, where an algorithm actively selects relevant batches of unlabeled examples for annotation. These examples could either belong to already known or to yet undiscovered classes. Our algorithm is based on a new generalization of the Expected Model Output Change principle for deep architectures and is especially tailored to deep neural networks. Furthermore, we show easy-to-implement approximations that yield efficient techniques for active selection. Empirical experiments show that our method outperforms currently used heuristics.