Recurrent Neural Networks for Person Re-identification Revisited

TL;DR

This paper revisits RNNs for person re-identification, proposing a simplified feed-forward model that matches or exceeds the accuracy of recurrent models while converging faster and enabling performance improvements.

Contribution

It introduces a simplified feed-forward architecture derived from RNNs that maintains accuracy and enhances training efficiency for person re-identification.

Findings

Feed-forward model achieves similar accuracy to RNNs.

Proposed training process improves re-identification performance.

Models converge faster with up to 5% accuracy gain.

Abstract

The task of person re-identification has recently received rising attention due to the high performance achieved by new methods based on deep learning. In particular, in the context of video-based re-identification, many state-of-the-art works have explored the use of Recurrent Neural Networks (RNNs) to process input sequences. In this work, we revisit this tool by deriving an approximation which reveals the small effect of recurrent connections, leading to a much simpler feed-forward architecture. Using the same parameters as the recurrent version, our proposed feed-forward architecture obtains very similar accuracy. More importantly, our model can be combined with a new training process to significantly improve re-identification performance. Our experiments demonstrate that the proposed models converge substantially faster than recurrent ones, with accuracy improvements by up to 5% on two datasets. The performance achieved is better or on par with other RNN-based person re-identification techniques.