2019/03/20 by Alessio Sarullo, Sarullo, Alessio, Tingting Mu +1
Computer Science · Medicine · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Imbalanced Data Classification Techniques #Multimodal Machine Learning Applications #Retinal Imaging and Analysis
paper · pdf · doi:10.48550/arxiv.1903.08456
openalex publication_date 2019/03/20 · openalex created_date 2019/04/01 · openalex updated_date 2026/07/28
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.