# A Safety Assurable Human-Inspired Perception Architecture

arXiv: https://arxiv.org/abs/2205.07862 · HTML: https://mlsanity.com/paper/2205.07862/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 51 references that are in the map.
- First posted on arXiv 10 May 2022.

## Builds on (most cited first, 17 of 17)

- [This Looks Like That: Deep Learning for Interpretable Image Recognition](https://mlsanity.com/paper/1806.10574/) (2018)
- [BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks](https://mlsanity.com/paper/1709.01686/) (2017)
- [A Survey of Embodied AI: From Simulators to Research Tasks](https://mlsanity.com/paper/2103.04918/) (2021)
- [Deep Learning for Case-Based Reasoning through Prototypes: A Neural Network that Explains Its Predictions](https://mlsanity.com/paper/1710.04806/) (2017)
- [Algorithms for Verifying Deep Neural Networks](https://mlsanity.com/paper/1903.06758/) (2019)
- [Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learning](https://mlsanity.com/paper/1803.04765/) (2018)
- [Inducing Causal Structure for Interpretable Neural Networks](https://mlsanity.com/paper/2112.00826/) (2021)
- [Beyond accuracy: quantifying trial-by-trial behaviour of CNNs and humans by measuring error consistency](https://mlsanity.com/paper/2006.16736/) (2020)
- [Thinking Fast and Slow in AI](https://mlsanity.com/paper/2010.06002/) (2020)
- [Interpretable Image Recognition with Hierarchical Prototypes](https://mlsanity.com/paper/1906.10651/) (2019)
- [Thinking Fast and Slow: Optimization Decomposition Across Timescales](https://mlsanity.com/paper/1704.07785/) (2017)
- [3D-Aware Scene Manipulation via Inverse Graphics](https://mlsanity.com/paper/1808.09351/) (2018)
- [Commonsense Visual Sensemaking for Autonomous Driving: On Generalised Neurosymbolic Online Abduction Integrating Vision and Semantics](https://mlsanity.com/paper/2012.14359/) (2020)
- [If a Human Can See It, So Should Your System: Reliability Requirements for Machine Vision Components](https://mlsanity.com/paper/2202.03930/) (2022)
- [The missing link: Developing a safety case for perception components in automated driving](https://mlsanity.com/paper/2108.13294/) (2021)
- [Cerberus: A Multi-headed Derenderer](https://mlsanity.com/paper/1905.11940/) (2019)
- [Biologically Inspired Visual System Architecture for Object Recognition in Autonomous Systems](https://mlsanity.com/paper/2002.03472/) (2020)

## Abstract (arXiv)

Although artificial intelligence-based perception (AIP) using deep neural networks (DNN) has achieved near human level performance, its well-known limitations are obstacles to the safety assurance needed in autonomous applications. These include vulnerability to adversarial inputs, inability to handle novel inputs and non-interpretability. While research in addressing these limitations is active, in this paper, we argue that a fundamentally different approach is needed to address them. Inspired by dual process models of human cognition, where Type 1 thinking is fast and non-conscious while Type 2 thinking is slow and based on conscious reasoning, we propose a dual process architecture for safe AIP. We review research on how humans address the simplest non-trivial perception problem, image classification, and sketch a corresponding AIP architecture for this task. We argue that this architecture can provide a systematic way of addressing the limitations of AIP using DNNs and an approach to assurance of human-level performance and beyond. We conclude by discussing what components of the architecture may already be addressed by existing work and what remains future work.