# A Partially Supervised Reinforcement Learning Framework for Visual Active Search

arXiv: https://arxiv.org/abs/2310.09689 · HTML: https://mlsanity.com/paper/2310.09689/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 36 references that are in the map.
- First posted on arXiv 15 Oct 2023.

## Builds on (most cited first, 19 of 19)

- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [DOTA: A Large-scale Dataset for Object Detection in Aerial Images](https://mlsanity.com/paper/1711.10398/) (2017)
- [Object Goal Navigation using Goal-Oriented Semantic Exploration](https://mlsanity.com/paper/2007.00643/) (2020)
- [Learning Loss for Active Learning](https://mlsanity.com/paper/1905.03677/) (2019)
- [AdaViT: Adaptive Vision Transformers for Efficient Image Recognition](https://mlsanity.com/paper/2111.15668/) (2021)
- [xView: Objects in Context in Overhead Imagery](https://mlsanity.com/paper/1802.07856/) (2018)
- [Resolution Adaptive Networks for Efficient Inference](https://mlsanity.com/paper/2003.07326/) (2020)
- [Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learning](https://mlsanity.com/paper/1812.00971/) (2018)
- [QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detection](https://mlsanity.com/paper/2103.09136/) (2021)
- [LiteEval: A Coarse-to-Fine Framework for Resource Efficient Video Recognition](https://mlsanity.com/paper/1912.01601/) (2019)
- [Learning When and Where to Zoom with Deep Reinforcement Learning](https://mlsanity.com/paper/2003.00425/) (2020)
- [Visual Navigation with Spatial Attention](https://mlsanity.com/paper/2104.09807/) (2021)
- [FOVEA: Foveated Image Magnification for Autonomous Navigation](https://mlsanity.com/paper/2108.12102/) (2021)
- [Alpha MAML: Adaptive Model-Agnostic Meta-Learning](https://mlsanity.com/paper/1905.07435/) (2019)
- [Efficient Object Detection in Large Images using Deep Reinforcement Learning](https://mlsanity.com/paper/1912.03966/) (2019)
- [Hard-Attention for Scalable Image Classification](https://mlsanity.com/paper/2102.10212/) (2021)
- [IS-COUNT: Large-scale Object Counting from Satellite Images with Covariate-based Importance Sampling](https://mlsanity.com/paper/2112.09126/) (2021)
- [What do navigation agents learn about their environment?](https://mlsanity.com/paper/2206.08500/) (2022)
- [A Visual Active Search Framework for Geospatial Exploration](https://mlsanity.com/paper/2211.15788/) (2022)

## Built on by (most cited first, 8 of 8)

- [GOMAA-Geo: GOal Modality Agnostic Active Geo-localization](https://mlsanity.com/paper/2406.01917/) (2024)
- [Amortized nonmyopic active search via deep imitation learning](https://mlsanity.com/paper/2405.15031/) (2024)
- [Active Geospatial Search for Efficient Tenant Eviction Outreach](https://mlsanity.com/paper/2412.17854/) (2024)
- [Comprehend, Divide, and Conquer: Feature Subspace Exploration via Multi-Agent Hierarchical Reinforcement Learning](https://mlsanity.com/paper/2504.17356/) (2025)
- [Online Feedback Efficient Active Target Discovery in Partially Observable Environments](https://mlsanity.com/paper/2505.06535/) (2025)
- [Active Target Discovery under Uninformative Prior: The Power of Permanent and Transient Memory](https://mlsanity.com/paper/2510.16676/) (2025)
- [Adapting Actively on the Fly: Relevance-Guided Online Meta-Learning with Latent Concepts for Geospatial Discovery](https://mlsanity.com/paper/2602.17605/) (2026)
- [DiffVAS: Diffusion-Guided Visual Active Search in Partially Observable Environments](https://mlsanity.com/paper/2605.15519/) (2026)

## Abstract (arXiv)

Visual active search (VAS) has been proposed as a modeling framework in which visual cues are used to guide exploration, with the goal of identifying regions of interest in a large geospatial area. Its potential applications include identifying hot spots of rare wildlife poaching activity, search-and-rescue scenarios, identifying illegal trafficking of weapons, drugs, or people, and many others. State of the art approaches to VAS include applications of deep reinforcement learning (DRL), which yield end-to-end search policies, and traditional active search, which combines predictions with custom algorithmic approaches. While the DRL framework has been shown to greatly outperform traditional active search in such domains, its end-to-end nature does not make full use of supervised information attained either during training, or during actual search, a significant limitation if search tasks differ significantly from those in the training distribution. We propose an approach that combines the strength of both DRL and conventional active search by decomposing the search policy into a prediction module, which produces a geospatial distribution of regions of interest based on task embedding and search history, and a search module, which takes the predictions and search history as input and outputs the search distribution. We develop a novel meta-learning approach for jointly learning the resulting combined policy that can make effective use of supervised information obtained both at training and decision time. Our extensive experiments demonstrate that the proposed representation and meta-learning frameworks significantly outperform state of the art in visual active search on several problem domains.