# Vendi Information Gain for Active Learning and its Application to Ecology

arXiv: https://arxiv.org/abs/2509.10390 · HTML: https://mlsanity.com/paper/2509.10390/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 43 references that are in the map.
- First posted on arXiv 12 Sep 2025.

## Builds on (most cited first, 22 of 22)

- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Deep Bayesian Active Learning with Image Data](https://mlsanity.com/paper/1703.02910/) (2017)
- [Recognition in Terra Incognita](https://mlsanity.com/paper/1807.04975/) (2018)
- [BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning](https://mlsanity.com/paper/1906.08158/) (2019)
- [The Vendi Score: A Diversity Evaluation Metric for Machine Learning](https://mlsanity.com/paper/2210.02410/) (2022)
- [Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding](https://mlsanity.com/paper/1511.02680/) (2015)
- [Seeing biodiversity: perspectives in machine learning for wildlife conservation](https://mlsanity.com/paper/2110.12951/) (2021)
- [Lazier Than Lazy Greedy](https://mlsanity.com/paper/1409.7938/) (2014)
- [Beyond Aesthetics: Cultural Competence in Text-to-Image Models](https://mlsanity.com/paper/2407.06863/) (2024)
- [Cousins Of The Vendi Score: A Family Of Similarity-Based Diversity Metrics For Science And Machine Learning](https://mlsanity.com/paper/2310.12952/) (2023)
- [Improving Geo-diversity of Generated Images with Contextualized Vendi Score Guidance](https://mlsanity.com/paper/2406.04551/) (2024)
- [Exploring Representativeness and Informativeness for Active Learning](https://mlsanity.com/paper/1904.06685/) (2019)
- [Quality-Weighted Vendi Scores And Their Application To Diverse Experimental Design](https://mlsanity.com/paper/2405.02449/) (2024)
- [Towards Geographic Inclusion in the Evaluation of Text-to-Image Models](https://mlsanity.com/paper/2405.04457/) (2024)
- [Vendi-RAG: Adaptively Trading-Off Diversity And Quality Significantly Improves Retrieval Augmented Generation With LLMs](https://mlsanity.com/paper/2502.11228/) (2025)
- [Automated wildlife image classification: An active learning tool for ecological applications](https://mlsanity.com/paper/2303.15823/) (2023)
- [Exploiting Diversity of Unlabeled Data for Label-Efficient Semi-Supervised Active Learning](https://mlsanity.com/paper/2207.12302/) (2022)
- [The Alpha-Alternator: Dynamic Adaptation To Varying Noise Levels In Sequences Using The Vendi Score For Improved Robustness and Performance](https://mlsanity.com/paper/2502.04593/) (2025)
- [The Vendiscope: An Algorithmic Microscope For Data Collections](https://mlsanity.com/paper/2502.10828/) (2025)
- [Nonmyopic Multiclass Active Search with Diminishing Returns for Diverse Discovery](https://mlsanity.com/paper/2202.03593/) (2022)
- [Nonmyopic Multifidelity Active Search](https://mlsanity.com/paper/2106.06356/) (2021)
- [VendiRL: A Framework for Self-Supervised Reinforcement Learning of Diversely Diverse Skills](https://mlsanity.com/paper/2509.02930/) (2025)

## Abstract (arXiv)

While monitoring biodiversity through camera traps has become an important endeavor for ecological research, identifying species in the captured image data remains a major bottleneck due to limited labeling resources. Active learning -- a machine learning paradigm that selects the most informative data to label and train a predictive model -- offers a promising solution, but typically focuses on uncertainty in the individual predictions without considering uncertainty across the entire dataset. We introduce a new active learning policy, Vendi information gain (VIG), that selects images based on their impact on dataset-wide prediction uncertainty, capturing both informativeness and diversity. We applied VIG to the Snapshot Serengeti dataset and compared it against common active learning methods. VIG needs only 3% of the available data to reach 75% accuracy, a level that baselines require more than 10% of the data to achieve. With 10% of the data, VIG attains 88% predictive accuracy, 12% higher than the best of the baselines. This improvement in performance is consistent across metrics and batch sizes, and we show that VIG also collects more diverse data in the feature space. VIG has broad applicability beyond ecology, and our results highlight its value for biodiversity monitoring in data-limited environments.