Robust and Interpretable Grounding of Spatial References with Relation Networks
원문 초록
Learning representations of spatial references in natural language is a key challenge in tasks like autonomous navigation and robotic manipulation. Recent work has investigated various neural architectures for learning multi-modal representations for spatial concepts. However, the lack of explicit reasoning over entities makes such approaches vulnerable to noise in input text or state observations. In this paper, we develop effective models for understanding spatial references in text that are robust and interpretable, without sacrificing performance. We design a text-conditioned \textit{relation network} whose parameters are dynamically computed with a cross-modal attention module to capture fine-grained spatial relations between entities. This design choice provides interpretability of learned intermediate outputs. Experiments across three tasks demonstrate that our model achieves superior performance, with a 17\% improvement in predicting goal locations and a 15\% improvement in robustness compared to state-of-the-art systems.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
FarSeg++: Foreground-Aware Relation Network for Geospatial Object Segmentation in High Spatial Resolution Remote Sensing Imagery
Multistage Relation Network With Dual-Metric for Few-Shot Hyperspectral Image Classification
PAC-MAN: Multi-Relation Network in Social Community for Personalized Hashtag Recommendation
GeoDistill: Geometry-Guided Self-Distillation for Weakly Supervised Cross-View Localization
Improve Underwater Object Detection through YOLOv12 Architecture and Physics-informed Augmentation
Enhancing Homophily-Heterophily Separation: Relation-Aware Learning in Heterogeneous Graphs
토론
이 논문과 연결된 포럼 글이 아직 없습니다.