# Introspection in Learned Semantic Scene Graph Localisation

arXiv: https://arxiv.org/abs/2510.07053 · HTML: https://mlsanity.com/paper/2510.07053/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 29 references that are in the map.
- First posted on arXiv 8 Oct 2025.

## Builds on (most cited first, 21 of 21)

- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Attention is not not Explanation](https://mlsanity.com/paper/1908.04626/) (2019)
- [Explainability in Graph Neural Networks: A Taxonomic Survey](https://mlsanity.com/paper/2012.15445/) (2020)
- [Kimera: an Open-Source Library for Real-Time Metric-Semantic Localization and Mapping](https://mlsanity.com/paper/1910.02490/) (2019)
- [Hydra: A Real-time Spatial Perception System for 3D Scene Graph Construction and Optimization](https://mlsanity.com/paper/2201.13360/) (2022)
- [Semantic Visual Localization](https://mlsanity.com/paper/1712.05773/) (2017)
- [Text2Loc: 3D Point Cloud Localization from Natural Language](https://mlsanity.com/paper/2311.15977/) (2023)
- [Interpretable Semantic Photo Geolocation](https://mlsanity.com/paper/2104.14995/) (2021)
- [GCN-SE: Attention as Explainability for Node Classification in Dynamic Graphs](https://mlsanity.com/paper/2110.05598/) (2021)
- [SemSegMap- 3D Segment-Based Semantic Localization](https://mlsanity.com/paper/2107.14715/) (2021)
- [BoxGraph: Semantic Place Recognition and Pose Estimation from 3D LiDAR](https://mlsanity.com/paper/2206.15154/) (2022)
- [SEM-GAT: Explainable Semantic Pose Estimation using Learned Graph Attention](https://mlsanity.com/paper/2308.03718/) (2023)
- [Contrastive Learning-based Sentence Encoders Implicitly Weight Informative Words](https://mlsanity.com/paper/2310.15921/) (2023)
- [Semantic Interpretation and Validation of Graph Attention-based Explanations for GNN Models](https://mlsanity.com/paper/2308.04220/) (2023)
- [That's My Point: Compact Object-centric LiDAR Pose Estimation for Large-scale Outdoor Localisation](https://mlsanity.com/paper/2403.04755/) (2024)
- [Revisiting Attention Weights as Explanations from an Information Theoretic Perspective](https://mlsanity.com/paper/2211.07714/) (2022)
- [NAR-*ICP: Neural Execution of Classical ICP-based Pointcloud Registration Algorithms](https://mlsanity.com/paper/2410.11031/) (2024)
- [Active Semantic Localization with Graph Neural Embedding](https://mlsanity.com/paper/2305.06141/) (2023)

## Abstract (arXiv)

This work investigates how semantics influence localisation performance and robustness in a learned self-supervised, contrastive semantic localisation framework. After training a localisation network on both original and perturbed maps, we conduct a thorough post-hoc introspection analysis to probe whether the model filters environmental noise and prioritises distinctive landmarks over routine clutter. We validate various interpretability methods and present a comparative reliability analysis. Integrated gradients and Attention Weights consistently emerge as the most reliable probes of learned behaviour. A semantic class ablation further reveals an implicit weighting in which frequent objects are often down-weighted. Overall, the results indicate that the model learns noise-robust, semantically salient relations about place definition, thereby enabling explainable registration under challenging visual and structural variations.