研究语义如何影响自监督定位模型的鲁棒性与可解释性
Introspection in Learned Semantic Scene Graph Localisation
- 通过后验分析探究模型是否过滤噪声并重视显著地标
- 集成梯度与注意力权重是最可靠的可解释性方法
- 频繁出现的物体常被自动降权，模型更关注语义显著特征
本文研究语义在自监督对比学习定位框架中对定位性能和鲁棒性的影响。在原始地图与扰动地图上训练定位网络后，进行细致的后验可解释性分析，考察模型是否能过滤环境噪声并优先关注显著地标而非普通杂乱信息。验证了多种可解释性方法，并进行了可靠性对比分析。结果表明，集成梯度与注意力权重始终是最可靠的模型行为探测工具。语义类别消融实验揭示模型存在隐式加权机制：常见物体通常被降权。总体而言，模型学会了对噪声具有鲁棒性的、语义显著的场景关系表征，从而在复杂视觉与结构变化下实现可解释的定位注册。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。