The Second Place Solution for ICCV2021 VIPriors Instance Segmentation Challenge

TL;DR

This paper presents a data-efficient instance segmentation method for the ICCV2021 VIPriors challenge, utilizing data augmentation, model selection, and training strategies without external data or pre-trained weights, achieving 40.2% AP.

Contribution

The paper introduces a novel combination of data augmentation, model improvements, and training strategies specifically designed for data-deficient instance segmentation tasks.

Findings

Achieved 40.2% AP on the test set

Effective data augmentation improved data-deficient training

Proposed training strategy enhanced performance

Abstract

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.