Log In Sign Up

Unsupervised Person Re-identification: Clustering and Fine-tuning

by   Hehe Fan, et al.

The superiority of deeply learned pedestrian representations has been reported in very recent literature of person re-identification (re-ID). In this paper, we consider the more pragmatic issue of learning a deep feature with no or only a few labels. We propose a progressive unsupervised learning (PUL) method to transfer pretrained deep representations to unseen domains. Our method is easy to implement and can be viewed as an effective baseline for unsupervised re-ID feature learning. Specifically, PUL iterates between 1) pedestrian clustering and 2) fine-tuning of the convolutional neural network (CNN) to improve the original model trained on the irrelevant labeled dataset. Since the clustering results can be very noisy, we add a selection operation between the clustering and fine-tuning. At the beginning when the model is weak, CNN is fine-tuned on a small amount of reliable examples which locate near to cluster centroids in the feature space. As the model becomes stronger in subsequent iterations, more images are being adaptively selected as CNN training samples. Progressively, pedestrian clustering and the CNN model are improved simultaneously until algorithm convergence. This process is naturally formulated as self-paced learning. We then point out promising directions that may lead to further improvement. Extensive experiments on three large-scale re-ID datasets demonstrate that PUL outputs discriminative features that improve the re-ID accuracy.


page 2

page 5


Temporal Continuity Based Unsupervised Learning for Person Re-Identification

Person re-identification (re-id) aims to match the same person from imag...

Pedestrian Alignment Network for Large-scale Person Re-identification

Person re-identification (person re-ID) is mostly viewed as an image ret...

Pose-Normalized Image Generation for Person Re-identification

Person Re-identification (re-id) faces two major challenges: the lack of...

Deep Transfer Learning for Person Re-identification

Person re-identification (Re-ID) poses a unique challenge to deep learni...

Unsupervised Person Re-Identification with Multi-Label Learning Guided Self-Paced Clustering

Although unsupervised person re-identification (Re-ID) has drawn increas...

Unsupervised Person Re-identification via Simultaneous Clustering and Consistency Learning

Unsupervised person re-identification (re-ID) has become an important to...

SVDNet for Pedestrian Retrieval

This paper proposes the SVDNet for retrieval problems, with focus on the...

Code Repositories



view repo