论文标题
LVIS Challenge的第一位解决方案2020：一个好的盒子不能保证一个好的面具
1st Place Solution of LVIS Challenge 2020: A Good Box is not a Guarantee of a Good Mask
论文作者
论文摘要
本文介绍了LVIS Challenge 2020的LVISTRALVER团队的解决方案。在这项工作中，LVIS数据集的两个特征主要考虑：长尾分布和高质量实例细分面罩。我们采用了两阶段的培训管道。在第一阶段，我们将EQL和自训练纳入学习通用表示。在第二阶段，我们利用平衡的组来促进分类器，并提出一种新颖的建议分配策略和新的平衡面具损失，以获得更精确的掩盖预测。最后，我们在LVIS V1.0 VAL和TEST-DEV拆分上达到41.5和41.2 AP，超过了基于X101-FPN-MaskRCNN的基线，这是一个较大的余量。
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.
