# The Second Place Solution for ICCV2021 VIPriors Instance Segmentation Challenge

arXiv: https://arxiv.org/abs/2112.01072 · HTML: https://mlsanity.com/paper/2112.01072/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 13 references that are in the map.
- First posted on arXiv 2 Dec 2021.

## Builds on (most cited first, 11 of 11)

- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Group Normalization](https://mlsanity.com/paper/1803.08494/) (2018)
- [Path Aggregation Network for Instance Segmentation](https://mlsanity.com/paper/1803.01534/) (2018)
- [Hybrid Task Cascade for Instance Segmentation](https://mlsanity.com/paper/1901.07518/) (2019)
- [Soft-NMS -- Improving Object Detection With One Line of Code](https://mlsanity.com/paper/1704.04503/) (2017)
- [SOLO: Segmenting Objects by Locations](https://mlsanity.com/paper/1912.04488/) (2019)
- [DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution](https://mlsanity.com/paper/2006.02334/) (2020)
- [GridMask Data Augmentation](https://mlsanity.com/paper/2001.04086/) (2020)
- [TensorMask: A Foundation for Dense Object Segmentation](https://mlsanity.com/paper/1903.12174/) (2019)
- [CenterMask: single shot instance segmentation with point representation](https://mlsanity.com/paper/2004.04446/) (2020)
- [SWA Object Detection](https://mlsanity.com/paper/2012.12645/) (2020)

## Built on by (most cited first, 2 of 2)

- [VIPriors 2: Visual Inductive Priors for Data-Efficient Deep Learning Challenges](https://mlsanity.com/paper/2201.08625/) (2022)
- [Data-Efficient Challenges in Visual Inductive Priors: A Retrospective](https://mlsanity.com/paper/2506.08612/) (2025)

## Abstract (arXiv)

The Visual Inductive Priors(VIPriors) for Data-Efficient Computer Vision challenges ask competitors to train models from scratch in a data-deficient setting. In this paper, we introduce the technical details of our submission to the ICCV2021 VIPriors instance segmentation challenge. Firstly, we designed an effective data augmentation method to improve the problem of data-deficient. Secondly, we conducted some experiments to select a proper model and made some improvements for this task. Thirdly, we proposed an effective training strategy which can improve the performance. Experimental results demonstrate that our approach can achieve a competitive result on the test set. According to the competition rules, we do not use any external image or video data and pre-trained weights. The implementation details above are described in section 2 and section 3. Finally, our approach can achieve 40.2%AP@0.50:0.95 on the test set of ICCV2021 VIPriors instance segmentation challenge.