1st Place Solution of LVIS Challenge 2020: A Good Box is not a Guarantee of a Good Mask
This work addresses instance segmentation for datasets with long-tailed distributions, offering incremental improvements in mask prediction accuracy.
The paper tackles the challenges of long-tailed distribution and high-quality mask requirements in the LVIS dataset for instance segmentation, achieving 41.5 AP on val and 41.2 AP on test-dev splits, which significantly outperforms the baseline.
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.