Introspection in Learned Semantic Scene Graph Localisation

• URL: http://arxiv.org/abs/2510.07053v1
• Date: Wed, 08 Oct 2025 14:21:45 GMT
• Title: Introspection in Learned Semantic Scene Graph Localisation
• Authors: Manshika Charvi Bissessur, Efimia Panagiotaki, Daniele De Martini,
• Abstract summary: This work investigates how semantics influence localisation performance and robustness in a self-supervised, contrastive semantic localisation framework.<n>We conduct a thorough post-hoc introspection analysis to probe whether the model filters environmental noise and prioritises distinctive landmarks over routine clutter.<n>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.
• Score: 7.222321327403328
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Toward Faithful Explanations in Acoustic Anomaly Detection [21.487734134424187]
  Interpretability is essential for user trust in real-world anomaly detection applications.<n>We compare a standard autoencoder (AE) with a mask autoencoder (MAE) in terms of detection performance and interpretability.<n>MAE consistently provides more faithful and temporally precise explanations, suggesting a better alignment with true anomalies.
  arXiv  Detail & Related papers  (2026-01-19T02:16:37Z)
• A Unified Reasoning Framework for Holistic Zero-Shot Video Anomaly Analysis [64.42659342276117]
  Most video-anomaly research stops at frame-wise detection, offering little insight into why an event is abnormal.<n>Recent video anomaly localization and video anomaly understanding methods improve explainability but remain data-dependent and task-specific.<n>We propose a unified reasoning framework that bridges the gap between temporal detection, spatial localization, and textual explanation.
  arXiv  Detail & Related papers  (2025-11-02T14:49:08Z)
• Semantic and Structural Analysis of Implicit Biases in Large Language Models: An Interpretable Approach [1.5749416770494704]
  It proposes an interpretable bias detection method aimed at identifying hidden social biases in model outputs.<n>The method combines nested semantic representation with a contextual contrast mechanism.<n>The evaluation focuses on several key metrics, such as bias detection accuracy, semantic consistency, and contextual sensitivity.
  arXiv  Detail & Related papers  (2025-08-08T09:21:10Z)
• Slow Feature Analysis on Markov Chains from Goal-Directed Behavior [0.0]
  This work investigates the effects of goal-directed behavior on value-function approximation in an idealized setting.<n>Three correction routes, which can potentially alleviate detrimental scaling effects, are evaluated and discussed.
  arXiv  Detail & Related papers  (2025-06-01T19:57:41Z)
• Unlearning-based Neural Interpretations [51.99182464831169]
  We show that current baselines defined using static functions are biased, fragile and manipulable.<n>We propose UNI to compute an (un)learnable, debiased and adaptive baseline by perturbing the input towards an unlearning direction of steepest ascent.
  arXiv  Detail & Related papers  (2024-10-10T16:02:39Z)
• Improving Network Interpretability via Explanation Consistency Evaluation [56.14036428778861]
  We propose a framework that acquires more explainable activation heatmaps and simultaneously increase the model performance. Specifically, our framework introduces a new metric, i.e., explanation consistency, to reweight the training samples adaptively in model learning. Our framework then promotes the model learning by paying closer attention to those training samples with a high difference in explanations.
  arXiv  Detail & Related papers  (2024-08-08T17:20:08Z)
• Adaptive Local-Component-aware Graph Convolutional Network for One-shot Skeleton-based Action Recognition [54.23513799338309]
  We present an Adaptive Local-Component-aware Graph Convolutional Network for skeleton-based action recognition. Our method provides a stronger representation than the global embedding and helps our model reach state-of-the-art.
  arXiv  Detail & Related papers  (2022-09-21T02:33:07Z)
• Causal Transportability for Visual Recognition [70.13627281087325]
  We show that standard classifiers fail because the association between images and labels is not transportable across settings. We then show that the causal effect, which severs all sources of confounding, remains invariant across domains. This motivates us to develop an algorithm to estimate the causal effect for image classification.
  arXiv  Detail & Related papers  (2022-04-26T15:02:11Z)
• Exploring Set Similarity for Dense Self-supervised Representation Learning [96.35286140203407]
  We propose to explore textbfset textbfsimilarity (SetSim) for dense self-supervised representation learning. We generalize pixel-wise similarity learning to set-wise one to improve the robustness because sets contain more semantic and structure information. Specifically, by resorting to attentional features of views, we establish corresponding sets, thus filtering out noisy backgrounds that may cause incorrect correspondences.
  arXiv  Detail & Related papers  (2021-07-19T09:38:27Z)
• Learning structure-aware semantic segmentation with image-level supervision [36.40302533324508]
  We argue that the lost structure information in CAM limits its application in downstream semantic segmentation. We introduce an auxiliary semantic boundary detection module, which penalizes the deteriorated predictions. Experimental results on the PASCAL-VOC dataset illustrate the effectiveness of the proposed solution.
  arXiv  Detail & Related papers  (2021-04-15T03:33:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.