# Active Visual Exploration Based on Attention-Map Entropy

arXiv: https://arxiv.org/abs/2303.06457 · HTML: https://mlsanity.com/paper/2303.06457/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 31 references that are in the map.
- First posted on arXiv 11 Mar 2023.

## Builds on (most cited first, 18 of 18)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Context Encoders: Feature Learning by Inpainting](https://mlsanity.com/paper/1604.07379/) (2016)
- [Intriguing Properties of Vision Transformers](https://mlsanity.com/paper/2105.10497/) (2021)
- [MAT: Mask-Aware Transformer for Large Hole Image Inpainting](https://mlsanity.com/paper/2203.15270/) (2022)
- [Omnivore: A Single Model for Many Visual Modalities](https://mlsanity.com/paper/2201.08377/) (2022)
- [An Exploration of Embodied Visual Exploration](https://mlsanity.com/paper/2001.02192/) (2020)
- [4Seasons: A Cross-Season Dataset for Multi-Weather SLAM in Autonomous Driving](https://mlsanity.com/paper/2009.06364/) (2020)
- [Processing of missing data by neural networks](https://mlsanity.com/paper/1805.07405/) (2018)
- [Patchwork: A Patch-wise Attention Network for Efficient Object Detection and Segmentation in Video Streams](https://mlsanity.com/paper/1904.01784/) (2019)
- [Sidekick Policy Learning for Active Visual Exploration](https://mlsanity.com/paper/1807.11010/) (2018)
- [Consistency driven Sequential Transformers Attention Model for Partially Observable Scenes](https://mlsanity.com/paper/2204.00656/) (2022)
- [Attend and Segment: Attention Guided Active Semantic Segmentation](https://mlsanity.com/paper/2007.11548/) (2020)
- [Glimpse-Attend-and-Explore: Self-Attention for Active Visual Exploration](https://mlsanity.com/paper/2108.11717/) (2021)
- [Where to Look Next: Unsupervised Active Visual Exploration on 360deg Input](https://mlsanity.com/paper/1909.10304/) (2019)
- [Visual Attention in Imaginative Agents](https://mlsanity.com/paper/2104.00177/) (2021)

## Built on by (most cited first, 13 of 13)

- [Training-free Diffusion Model Adaptation for Variable-Sized Text-to-Image Synthesis](https://mlsanity.com/paper/2306.08645/) (2023)
- [AdaGlimpse: Active Visual Exploration with Arbitrary Glimpse Position and Scale](https://mlsanity.com/paper/2404.03482/) (2024)
- [FlySearch: Exploring how vision-language models explore](https://mlsanity.com/paper/2506.02896/) (2025)
- [Beyond [cls]: Exploring the true potential of Masked Image Modeling representations](https://mlsanity.com/paper/2412.03215/) (2024)
- [ToProVAR: Efficient Visual Autoregressive Modeling via Tri-Dimensional Entropy-Aware Semantic Analysis and Sparsity Optimization](https://mlsanity.com/paper/2602.22948/) (2026)
- [Beyond Grids: Exploring Elastic Input Sampling for Vision Transformers](https://mlsanity.com/paper/2309.13353/) (2023)
- [TORE: Token Recycling in Vision Transformers for Efficient Active Visual Exploration](https://mlsanity.com/paper/2311.15335/) (2023)
- [CanViT: Toward Active-Vision Foundation Models](https://mlsanity.com/paper/2603.22570/) (2026)
- [HRVConformer: Neonatal Hypoxic-Ischemic Encephalopathy Classification from the Heart Rate signals](https://mlsanity.com/paper/2605.26190/) (2026)
- [Recursive Visual Imagination and Adaptive Linguistic Grounding for Vision Language Navigation](https://mlsanity.com/paper/2507.21450/) (2025)
- [QSilk: Micrograin Stabilization and Adaptive Quantile Clipping for Detail-Friendly Latent Diffusion](https://mlsanity.com/paper/2510.15761/) (2025)
- [Controlling Motion Transfer in Diffusion Transformers via Attention Heads](https://mlsanity.com/paper/2607.11081/) (2026)
- [Efficient Semantic Understanding from Digital Foveation](https://mlsanity.com/paper/2609.04088/) (2026)

## Abstract (arXiv)

Active visual exploration addresses the issue of limited sensor capabilities in real-world scenarios, where successive observations are actively chosen based on the environment. To tackle this problem, we introduce a new technique called Attention-Map Entropy (AME). It leverages the internal uncertainty of the transformer-based model to determine the most informative observations. In contrast to existing solutions, it does not require additional loss components, which simplifies the training. Through experiments, which also mimic retina-like sensors, we show that such simplified training significantly improves the performance of reconstruction, segmentation and classification on publicly available datasets.