A Technical Report for ICCV 2021 VIPriors Re-identification Challenge

TL;DR

This paper presents a solution for person re-identification in the VIPriors Challenge 2021, achieving top performance without using pretrained models by employing advanced data processing, model design, and ensemble techniques.

Contribution

The paper introduces a novel approach combining data augmentation, occlusion pre-processing, multiple backbones, and ensemble methods to excel in training from scratch for re-identification.

Findings

Achieved 96.5154% mAP, ranking first in the challenge.

Effective use of data augmentation and occlusion handling improves discriminative features.

Post-processing ensemble methods significantly boost final accuracy.

Abstract

Person re-identification has always been a hot and challenging task. This paper introduces our solution for the re-identification track in VIPriors Challenge 2021. In this challenge, the difficulty is how to train the model from scratch without any pretrained weight. In our method, we show use state-of-the-art data processing strategies, model designs, and post-processing ensemble methods, it is possible to overcome the difficulty of data shortage and obtain competitive results. (1) Both image augmentation strategy and novel pre-processing method for occluded images can help the model learn more discriminative features. (2) Several strong backbones and multiple loss functions are used to learn more representative features. (3) Post-processing techniques including re-ranking, automatic query expansion, ensemble learning, etc., significantly improve the final performance. The final score of our team (ALONG) is 96.5154% mAP, ranking first in the leaderboard.