# Active Observer Visual Problem-Solving Methods are Dynamically Hypothesized, Deployed and Tested

arXiv: https://arxiv.org/abs/2108.08145 · HTML: https://mlsanity.com/paper/2108.08145/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 36 references that are in the map.
- First posted on arXiv 18 Aug 2021.

## Builds on (most cited first, 9 of 9)

- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [A Survey of Deep Active Learning](https://mlsanity.com/paper/2009.00236/) (2020)
- [The Consciousness Prior](https://mlsanity.com/paper/1709.08568/) (2017)
- [Revisiting Active Perception](https://mlsanity.com/paper/1603.02729/) (2016)
- [Beyond imitation: Zero-shot task transfer on robots by learning concepts as cognitive programs](https://mlsanity.com/paper/1812.02788/) (2018)
- [PESAO: Psychophysical Experimental Setup for Active Observers](https://mlsanity.com/paper/2009.09933/) (2020)
- [Blocks World Revisited: The Effect of Self-Occlusion on Classification by Convolutional Neural Networks](https://mlsanity.com/paper/2102.12911/) (2021)
- [STAR-RT: Visual attention for real-time video game playing](https://mlsanity.com/paper/1711.09464/) (2017)
- [On the Control of Attentional Processes in Vision](https://mlsanity.com/paper/2101.01533/) (2021)

## Abstract (arXiv)

The STAR architecture was designed to test the value of the full Selective Tuning model of visual attention for complex real-world visuospatial tasks and behaviors. However, knowledge of how humans solve such tasks in 3D as active observers is lean. We thus devised a novel experimental setup and examined such behavior. We discovered that humans exhibit a variety of problem-solving strategies whose breadth and complexity are surprising and not easily handled by current methodologies. It is apparent that solution methods are dynamically composed by hypothesizing sequences of actions, testing them, and if they fail, trying different ones. The importance of active observation is striking as is the lack of any learning effect. These results inform our Cognitive Program representation of STAR extending its relevance to real-world tasks.