# 3rd Place Scheme on Instance Segmentation Track of ICCV 2021 VIPriors Challenges

arXiv: https://arxiv.org/abs/2110.00242 · HTML: https://mlsanity.com/paper/2110.00242/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 20 references that are in the map.
- First posted on arXiv 1 Oct 2021.

## Builds on (most cited first, 17 of 17)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [Path Aggregation Network for Instance Segmentation](https://mlsanity.com/paper/1803.01534/) (2018)
- [Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation](https://mlsanity.com/paper/2012.07177/) (2020)
- [Hybrid Task Cascade for Instance Segmentation](https://mlsanity.com/paper/1901.07518/) (2019)
- [Cascade R-CNN: High Quality Object Detection and Instance Segmentation](https://mlsanity.com/paper/1906.09756/) (2019)
- [DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution](https://mlsanity.com/paper/2006.02334/) (2020)
- [CenterMask : Real-Time Anchor-Free Instance Segmentation](https://mlsanity.com/paper/1911.06667/) (2019)
- [Instances as Queries](https://mlsanity.com/paper/2105.01928/) (2021)
- [CBNet: A Composite Backbone Network Architecture for Object Detection](https://mlsanity.com/paper/2107.00420/) (2021)
- [BridgeNet: A Continuity-Aware Probabilistic Network for Age Estimation](https://mlsanity.com/paper/1904.03358/) (2019)
- [On the Importance of Visual Context for Data Augmentation in Scene Understanding](https://mlsanity.com/paper/1809.02492/) (2018)
- [Reasoning Graph Networks for Kinship Verification: from Star-shaped to Hierarchical](https://mlsanity.com/paper/2109.02219/) (2021)

## Abstract (arXiv)

In this paper, we introduce a data-efficient instance segmentation method we used in the 2021 VIPriors Instance Segmentation Challenge. Our solution is a modified version of Swin Transformer, based on the mmdetection which is a powerful toolbox. To solve the problem of lack of data, we utilize data augmentation including random flip and multiscale training to train our model. During inference, multiscale fusion is used to boost the performance. We only use a single GPU during the whole training and testing stages. In the end, our team achieved the result of 0.366 for AP@0.50:0.95 on the test set, which is competitive with other top-ranking methods while only one GPU is used. Besides, our method achieved the AP@0.50:0.95 (medium) of 0.592, which ranks second among all contestants. In the end, our team ranked third among all the contestants, as announced by the organizers.