On Class Imbalance and Background Filtering in Visual Relationship Detection
원문 초록
In this paper we investigate the problems of class imbalance and irrelevant relationships in Visual Relationship Detection (VRD). State-of-the-art deep VRD models still struggle to predict uncommon classes, limiting their applicability. Moreover, many methods are incapable of properly filtering out background relationships while predicting relevant ones. Although these problems are very apparent, they have both been overlooked so far. We analyse why this is the case and propose modifications to both model and training to alleviate the aforementioned issues, as well as suggesting new measures to complement existing ones and give a more holistic picture of the efficacy of a model.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
METOR: A Unified Framework for Mutual Enhancement of Objects and Relationships in Open-vocabulary Video Visual Relationship Detection
Groupwise Query Specialization and Quality-Aware Multi-Assignment for Transformer-based Visual Relationship Detection
Video Relationship Detection Using Mixture of Experts
Self-Supervised Learning for Visual Relationship Detection through Masked Bounding Box Reconstruction
STUPD: A Synthetic Dataset for Spatial and Temporal Relation Reasoning
Unified Visual Relationship Detection with Vision and Language Models
토론
이 논문과 연결된 포럼 글이 아직 없습니다.