1st Place Solution of LVIS Challenge 2020: A Good Box is not a Guarantee of a Good Mask
By Jingru Tan, Gang Zhang, Hanming Deng, Changbao Wang, Lewei Lu, Quanquan Li, Jifeng Dai. 2020
19 citations recorded by the source corpus.
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.
Subfields: Civil and Structural Engineering, Computer Vision and Pattern Recognition, Emergency Medical Services, Pulmonary and Respiratory Medicine, Evaluation & Benchmarks
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Civil and Structural Engineering
In Computer Vision and Pattern Recognition
- Anelia Angelova
- In-So Kweon
- Luc Van Gool
- Dacheng Tao
- Jitendra Malik
- Weicheng Kuo
- Xiaogang Wang
- Ming-Hsuan Yang
In Evaluation & Benchmarks
- Weicheng Kuo
- In-So Kweon
- Anelia Angelova
- Dahun Kim
- Tsung-Yi Lin
- Kaiming He
- Chunhua Shen
- Ross B. Girshick
Citations in the corpus
- Learning Open-World Object Proposals without Learning to Classify (2021, background): “Large vocabulary detection has gained much attention lately in research community [22, 24, 52, 65] because the problem captures the Zipf’s law of visual world, i.”