# Plants Don't Walk on the Street: Common-Sense Reasoning for Reliable Semantic Segmentation

arXiv: https://arxiv.org/abs/2104.09254 · HTML: https://mlsanity.com/paper/2104.09254/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 28 references that are in the map.
- First posted on arXiv 19 Apr 2021.

## Builds on (most cited first, 6 of 6)

- [Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming](https://mlsanity.com/paper/1907.07484/) (2019)
- [Informed Machine Learning -- A Taxonomy and Survey of Integrating Knowledge into Learning Systems](https://mlsanity.com/paper/1903.12394/) (2019)
- [Deep Semantic Segmentation for Automated Driving: Taxonomy, Roadmap and Challenges](https://mlsanity.com/paper/1707.02432/) (2017)
- [Integrating Knowledge and Reasoning in Image Understanding](https://mlsanity.com/paper/1906.09954/) (2019)
- [Hinge-loss Markov Random Fields: Convex Inference for Structured Prediction](https://mlsanity.com/paper/1309.6813/) (2013)
- [Complex Events Recognition under Uncertainty in a Sensor Network](https://mlsanity.com/paper/1411.0085/) (2014)

## Built on by (most cited first, 1 of 1)

- [Towards a Systematic Risk Assessment of Deep Neural Network Limitations in Autonomous Driving Perception](https://mlsanity.com/paper/2604.20895/) (2026)

## Abstract (arXiv)

Data-driven sensor interpretation in autonomous driving can lead to highly implausible predictions as can most of the time be verified with common-sense knowledge. However, learning common knowledge only from data is hard and approaches for knowledge integration are an active research area. We propose to use a partly human-designed, partly learned set of rules to describe relations between objects of a traffic scene on a high level of abstraction. In doing so, we improve and robustify existing deep neural networks consuming low-level sensor information. We present an initial study adapting the well-established Probabilistic Soft Logic (PSL) framework to validate and improve on the problem of semantic segmentation. We describe in detail how we integrate common knowledge into the segmentation pipeline using PSL and verify our approach in a set of experiments demonstrating the increase in robustness against several severe image distortions applied to the A2D2 autonomous driving data set.