2020/09/03 by Jingru Tan, Tan, Jingru, Gang Zhang +11 · 1 citation
Engineering · Health Professions · Medicine · #Central Venous Catheters and Hemodialysis #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Infrastructure Maintenance and Monitoring #Prostate Cancer Diagnosis and Treatment
paper · pdf · doi:10.48550/arxiv.2009.01559
openalex publication_date 2020/09/03 · openalex created_date 2020/09/08 · openalex updated_date 2026/07/28
This article introduces the solutions of the team lvisTraveler for LVIS Challenge 2020. In this work, two characteristics of LVIS dataset are mainly considered: the long-tailed distribution and high quality instance segmentation mask. We adopt a two-stage training pipeline. In the first stage, we incorporate EQL and self-training to learn generalized representation. In the second stage, we utilize Balanced GroupSoftmax to promote the classifier, and propose a novel proposal assignment strategy and a new balanced mask loss for mask head to get more precise mask predictions. Finally, we achieve 41.5 and 41.2 AP on LVIS v1.0 val and test-dev splits respectively, outperforming the baseline based on X101-FPN-MaskRCNN by a large margin.