paper-with-me

홈 › Papers

Introspection in Learned Semantic Scene Graph Localisation

2025-10-08 · Manshika Charvi Bissessur, Efimia Panagiotaki, Daniele De Martini 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.

📄 PDF Abstract BibTeX arXiv:2510.07053

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Spatial Commonsense Graph for Object Localisation in Partial Scenes

2022-03-10 · CVPR 2022 1 · Francesco Giuliari, Geri Skenderi, Marco Cristani, Yiming Wang 외

We solve object localisation in partial scenes, a new problem of estimating the unknown position of an object (e.g. where is the bag?) given a partial 3D scan of a scene. The proposed solution is based on a novel scene g…

Graph Neural NetworkObjectPosition

Leveraging commonsense for object localisation in partial scenes

2022-11-01 · Francesco Giuliari, Geri Skenderi, Marco Cristani, Alessio Del Bue 외

We propose an end-to-end solution to address the problem of object localisation in partial scenes, where we aim to estimate the position of an object in an unknown area given only a partial 3D scan of the scene. We propo…

Graph Neural NetworkObjectPosition

LFA: Layer Feature Attention for Run-Time Introspection of 2D Object Detectors in Automated Driving

2026-05-29 · Mert Keser, Alois Knoll arxiv

Reliable object detection is critical for automated driving, yet even state-of-the-art detectors inevitably make errors that can compromise safety. Introspection methods that predict detector failures enable safer deploy…

Scene UnderstandingObject Detection

Self-Supervised Localisation between Range Sensors and Overhead Imagery

2020-06-03 · Tim Y. Tang, Daniele De Martini, Shangzhe Wu, Paul Newman

Publicly available satellite imagery can be an ubiquitous, cheap, and powerful tool for vehicle localisation when a prior sensor map is unavailable. However, satellite images are not directly comparable to data from grou…

Large Scale Joint Semantic Re-Localisation and Scene Understanding via Globally Unique Instance Coordinate Regression

2019-09-23 · Ignas Budvytis, Marvin Teichmann, Tomas Vojir, Roberto Cipolla

In this work we present a novel approach to joint semantic localisation and scene understanding. Our work is motivated by the need for localisation algorithms which not only predict 6-DoF camera pose but also simultaneou…

3D geometryAutonomous DrivingCamera Pose EstimationPose Estimation+2