# Projection: A Mechanism for Human-like Reasoning in Artificial Intelligence

arXiv: https://arxiv.org/abs/2103.13512 · HTML: https://mlsanity.com/paper/2103.13512/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 103 references that are in the map.
- First posted on arXiv 24 Mar 2021.

## Builds on (most cited first, 24 of 24)

- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering](https://mlsanity.com/paper/1707.07998/) (2017)
- [Perceiver: General Perception with Iterative Attention](https://mlsanity.com/paper/2103.03206/) (2021)
- [AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions](https://mlsanity.com/paper/1705.08421/) (2017)
- [Pose Guided Person Image Generation](https://mlsanity.com/paper/1705.09368/) (2017)
- [How to represent part-whole hierarchies in a neural network](https://mlsanity.com/paper/2102.12627/) (2021)
- [CAN: Creative Adversarial Networks, Generating "Art" by Learning About Styles and Deviating from Style Norms](https://mlsanity.com/paper/1706.07068/) (2017)
- [An Analysis of Visual Question Answering Algorithms](https://mlsanity.com/paper/1703.09684/) (2017)
- [Coordination Among Neural Modules Through a Shared Global Workspace](https://mlsanity.com/paper/2103.01197/) (2021)
- [Neural Production Systems: Learning Rule-Governed Visual Dynamics](https://mlsanity.com/paper/2103.01937/) (2021)
- [Recent Advances in Natural Language Inference: A Survey of Benchmarks, Resources, and Approaches](https://mlsanity.com/paper/1904.01172/) (2019)
- [Dark, Beyond Deep: A Paradigm Shift to Cognitive AI with Humanlike Common Sense](https://mlsanity.com/paper/2004.09044/) (2020)
- [Neural Task Graphs: Generalizing to Unseen Tasks from a Single Video Demonstration](https://mlsanity.com/paper/1807.03480/) (2018)
- [Learning to Make Analogies by Contrasting Abstract Relational Structure](https://mlsanity.com/paper/1902.00120/) (2019)
- [Learning to Combine Top-Down and Bottom-Up Signals in Recurrent Neural Networks with Attention over Modules](https://mlsanity.com/paper/2006.16981/) (2020)
- [Deep Nets: What have they ever done for Vision?](https://mlsanity.com/paper/1805.04025/) (2018)
- [Going in circles is the way forward: the role of recurrence in visual inference](https://mlsanity.com/paper/2003.12128/) (2020)
- [A Better Baseline for AVA](https://mlsanity.com/paper/1807.10066/) (2018)
- [The ActivityNet Large-Scale Activity Recognition Challenge 2018 Summary](https://mlsanity.com/paper/1808.03766/) (2018)
- [From explanation to synthesis: Compositional program induction for learning from demonstration](https://mlsanity.com/paper/1902.10657/) (2019)
- [Adapting Everyday Manipulation Skills to Varied Scenarios](https://mlsanity.com/paper/1803.02743/) (2018)
- [Auto-conditioned Recurrent Mixture Density Networks for Learning Generalizable Robot Skills](https://mlsanity.com/paper/1810.00146/) (2018)
- [Transfer of Tool Affordance and Manipulation Cues with 3D Vision Data](https://mlsanity.com/paper/1710.04970/) (2017)

## Built on by (most cited first, 2 of 2)

- [Recent Advances in Neural Text Generation: A Task-Agnostic Survey](https://mlsanity.com/paper/2203.03047/) (2022)
- [Do AI Agents Know When a Task Is Simple? Toward Complexity-Aware Reasoning and Execution](https://mlsanity.com/paper/2607.13034/) (2026)

## Abstract (arXiv)

Artificial Intelligence systems cannot yet match human abilities to apply knowledge to situations that vary from what they have been programmed for, or trained for. In visual object recognition methods of inference exploiting top-down information (from a model) have been shown to be effective for recognising entities in difficult conditions. Here this type of inference, called `projection', is shown to be a key mechanism to solve the problem of applying knowledge to varied or challenging situations, across a range of AI domains, such as vision, robotics, or language. Finally the relevance of projection to tackling the commonsense knowledge problem is discussed.