Weakly supervised discriminative feature learning with state information for person identification

TL;DR

This paper introduces a weakly supervised learning approach that leverages state information, such as camera view and pose labels, to improve unsupervised person re-identification and face recognition, outperforming existing methods.

Contribution

The work proposes a novel weak supervision method using state information to refine pseudo labels, enhancing unsupervised discriminative feature learning for person and face recognition.

Findings

Outperforms state-of-the-art on Duke-reID, MultiPIE, and CFP datasets.

Achieves results comparable to supervised fine-tuning.

Utilizes simple pseudo label model with state-based refinement.

Abstract

Unsupervised learning of identity-discriminative visual feature is appealing in real-world tasks where manual labelling is costly. However, the images of an identity can be visually discrepant when images are taken under different states, e.g. different camera views and poses. This visual discrepancy leads to great difficulty in unsupervised discriminative learning. Fortunately, in real-world tasks we could often know the states without human annotation, e.g. we can easily have the camera view labels in person re-identification and facial pose labels in face recognition. In this work we propose utilizing the state information as weak supervision to address the visual discrepancy caused by different states. We formulate a simple pseudo label model and utilize the state information in an attempt to refine the assigned pseudo labels by the weakly supervised decision boundary rectification and weakly supervised feature drift regularization. We evaluate our model on unsupervised person re-identification and pose-invariant face recognition. Despite the simplicity of our method, it could outperform the state-of-the-art results on Duke-reID, MultiPIE and CFP datasets with a standard ResNet-50 backbone. We also find our model could perform comparably with the standard supervised fine-tuning results on the three datasets. Code is available at https://github.com/KovenYu/state-information