Unleashing the Potential of Unsupervised Pre-Training with Intra-Identity Regularization for Person Re-Identification

12/01/2021
by   Zizheng Yang, et al.
0

Existing person re-identification (ReID) methods typically directly load the pre-trained ImageNet weights for initialization. However, as a fine-grained classification task, ReID is more challenging and exists a large domain gap between ImageNet classification. Inspired by the great success of self-supervised representation learning with contrastive objectives, in this paper, we design an Unsupervised Pre-training framework for ReID based on the contrastive learning (CL) pipeline, dubbed UP-ReID. During the pre-training, we attempt to address two critical issues for learning fine-grained ReID features: (1) the augmentations in CL pipeline may distort the discriminative clues in person images. (2) the fine-grained local features of person images are not fully-explored. Therefore, we introduce an intra-identity (I^2-)regularization in the UP-ReID, which is instantiated as two constraints coming from global image aspect and local patch aspect: a global consistency is enforced between augmented and original person images to increase robustness to augmentation, while an intrinsic contrastive constraint among local patches of each image is employed to fully explore the local discriminative clues. Extensive experiments on multiple popular Re-ID datasets, including PersonX, Market1501, CUHK03, and MSMT17, demonstrate that our UP-ReID pre-trained model can significantly benefit the downstream ReID fine-tuning and achieve state-of-the-art performance. Codes and models will be released to https://github.com/Frost-Yang-99/UP-ReID.

READ FULL TEXT

page 1

page 3

page 5

page 13

research
03/08/2022

Part-Aware Self-Supervised Pre-Training for Person Re-Identification

In person re-identification (ReID), very recent researches have validate...
research
08/17/2023

Identity-Seeking Self-Supervised Representation Learning for Generalizable Person Re-identification

This paper aims to learn a domain-generalizable (DG) person re-identific...
research
09/04/2023

Unified Pre-training with Pseudo Texts for Text-To-Image Person Re-identification

The pre-training task is indispensable for the text-to-image person re-i...
research
12/12/2021

Self-Supervised Modality-Aware Multiple Granularity Pre-Training for RGB-Infrared Person Re-Identification

While RGB-Infrared cross-modality person re-identification (RGB-IR ReID)...
research
03/08/2021

Unsupervised Pretraining for Object Detection by Patch Reidentification

Unsupervised representation learning achieves promising performances in ...
research
03/30/2022

Large-Scale Pre-training for Person Re-identification with Noisy Labels

This paper aims to address the problem of pre-training for person re-ide...
research
10/15/2020

Unsupervised Constrative Person Re-identification

Person re-identification (ReID) aims at searching the same identity pers...

Please sign up or login with your details

Forgot password? Click here to reset