Unsupervised Attention Based Instance Discriminative Learning for Person Re-Identification

TL;DR

This paper introduces an unsupervised person re-identification framework that uses a novel attention mechanism and joint clustering to handle large intra-class variations without pre-training, achieving superior results.

Contribution

The paper presents a new unsupervised learning approach with an attention mechanism that reduces parameters and improves discriminability in person re-identification.

Findings

Outperforms state-of-the-art methods on Market1501 and DukeMTMC-reID datasets.

Effectively handles large intra-class variations without pre-training.

Reduces model complexity by 59.6% through a new attention mechanism.

Abstract

Recent advances in person re-identification have demonstrated enhanced discriminability, especially with supervised learning or transfer learning. However, since the data requirements---including the degree of data curations---are becoming increasingly complex and laborious, there is a critical need for unsupervised methods that are robust to large intra-class variations, such as changes in perspective, illumination, articulated motion, resolution, etc. Therefore, we propose an unsupervised framework for person re-identification which is trained in an end-to-end manner without any pre-training. Our proposed framework leverages a new attention mechanism that combines group convolutions to (1) enhance spatial attention at multiple scales and (2) reduce the number of trainable parameters by 59.6%. Additionally, our framework jointly optimizes the network with agglomerative clustering and instance learning to tackle hard samples. We perform extensive analysis using the Market1501 and DukeMTMC-reID datasets to demonstrate that our method consistently outperforms the state-of-the-art methods (with and without pre-trained weights).