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

Dengpan Fu, Dongdong Chen 0001, Hao Yang, Jianmin Bao, Lu Yuan, Lei Zhang, Houqiang Li, Fang Wen, Dong Chen 0003

Abstract

Person Re-identification (Re-ID) typically relies on models pre-trained on ImageNet, which suffers from a significant domain gap. While unsupervised pre-training on person-specific data has shown promise, it often ignores temporal cues in video. This paper introduces LUPerson-NL, a massive dataset of 10 million images with 430,000 identities automatically labeled via video tracklets. To address the inherent noise in these labels, we propose the Pre-training with Noisy Labels (PNL) framework. PNL jointly learns feature representations and rectifies labels through prototype-based and label-guided contrastive learning. Our approach significantly outperforms ImageNet-supervised and unsupervised pre-training across major benchmarks, particularly in low-data regimes.

Introduction

The performance of Person Re-identification (Re-ID) systems is heavily dependent on the quality and scale of training data. However, manually labeling millions of images is prohibitively expensive. Existing methods often leverage ImageNet pre-training, but the semantic gap between generic objects and human pedestrians limits its effectiveness. Recent efforts in unsupervised pre-training (e.g., LUPerson) mitigate this gap but fail to utilize the "free" temporal supervision available in raw video tracklets.

This work bridges this gap by utilizing automatically generated, albeit noisy, labels from video tracking systems. We present LUPerson-NL, a large-scale dataset derived from 21,000 video scenes, and the PNL framework designed to learn robust representations from this noisy data.

The LUPerson-NL Dataset

Using the FairMOT tracker on street-view videos, the authors extracted over 10 million images. Each tracklet is assigned an identity, but tracking errors introduce two primary types of noise:

  • Noise-I (Fragmentation): A single individual is split into multiple IDs.
  • Noise-II (Drift): Different individuals are incorrectly assigned the same ID.

Despite these errors, the sheer scale and domain relevance of LUPerson-NL provide a superior foundation for Re-ID compared to generic datasets.

The PNL Framework

The PNL framework addresses label noise through three integrated components:

  1. Supervised Re-ID Learning: A classification module that learns from current labels.
  2. Prototype-based Contrastive Learning: The model maintains identity centroids (prototypes). By comparing image features to these prototypes, the system identifies and rectifies label errors.
  3. Label-guided Contrastive Learning: An extension of contrastive learning that uses rectified labels to refine the feature space, pulling similar identities together while pushing dissimilar ones apart.
The PNL framework jointly optimizes classification and contrastive objectives to rectify noisy tracklet labels during pre-training.

Experimental Results

We evaluated PNL-pre-trained models on standard benchmarks including Market1501, DukeMTMC-reID, MSMT17, and CUHK03.

Performance and Scaling

PNL consistently outperforms both ImageNet-supervised and unsupervised LUPerson pre-training. On CUHK03, PNL achieves a 5.7% mAP improvement over unsupervised methods. As shown in the scaling analysis, the performance gap is most pronounced when downstream training data is scarce. For instance, with only 10% of the Market1501 training set, PNL improves mAP by 15.6% over unsupervised pre-training.

Comparison of mAP (%) across different data scales on Market1501 and DukeMTMC-reID using MGN and IDE architectures. PNL (orange) consistently outperforms unsupervised (blue) and ImageNet (yellow) baselines.

Key Insights

  • Self-Correction: The "rectification loop" allows the model to improve its own labels as its feature representation matures. As prototypes become more accurate, label rectification becomes more reliable.
  • Domain Alignment: Pre-training on person-centric data, even with noise, is more effective than high-quality pre-training on unrelated domains like ImageNet.

Conclusion

LUPerson-NL and the PNL framework demonstrate that large-scale, noisy, automatically-labeled video data is a powerful resource for Re-ID. By actively rectifying labels during pre-training, PNL achieves state-of-the-art results and shows remarkable robustness in data-constrained scenarios. Future work will explore more sophisticated tracking algorithms to further improve the quality of initial labels.

Summary updated

Abstract

This paper aims to address the problem of pre-training for person re-identification (Re-ID) with noisy labels. To setup the pre-training task, we apply a simple online multi-object tracking system on raw videos of an existing unlabeled Re-ID dataset "LUPerson" nd build the Noisy Labeled variant called "LUPerson-NL". Since theses ID labels automatically derived from tracklets inevitably contain noises, we develop a large-scale Pre-training framework utilizing Noisy Labels (PNL), which consists of three learning modules: supervised Re-ID learning, prototype-based contrastive learning, and label-guided contrastive learning. In principle, joint learning of these three modules not only clusters similar examples to one prototype, but also rectifies noisy labels based on the prototype assignment. We demonstrate that learning directly from raw videos is a promising alternative for pre-training, which utilizes spatial and temporal correlations as weak supervision. This simple pre-training task provides a scalable way to learn SOTA Re-ID representations from scratch on "LUPerson-NL" without bells and whistles. For example, by applying on the same supervised Re-ID method MGN, our pre-trained model improves the mAP over the unsupervised pre-training counterpart by 5.7%, 2.2%, 2.3% on CUHK03, DukeMTMC, and MSMT17 respectively. Under the small-scale or few-shot setting, the performance gain is even more significant, suggesting a better transferability of the learned representation. Code is available at https://github.com/DengpanFu/LUPerson-NL
BibTeX
@inproceedings{fu2022large,
  author = {Dengpan Fu and Dongdong Chen and Hao Yang and Jianmin Bao and Lu Yuan and Lei Zhang and Houqiang Li and Fang Wen and Dong Chen},
  title = {{Large-Scale Pre-training for Person Re-identification with Noisy Labels}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year = {2022},
}
Figure