Parameter-Free Spatial Attention Network for Person Re-Identification

TL;DR

This paper introduces a parameter-free spatial attention layer that models spatial relations among features, improving person re-identification accuracy across multiple benchmarks without additional parameters.

Contribution

It proposes a novel, parameter-free spatial attention mechanism that enhances person re-identification models by capturing global spatial relations.

Findings

Achieves 94.7% rank-1 accuracy on Market-1501

Outperforms state-of-the-art on DukeMTMC-ReID

Improves performance on CUHK03 datasets

Abstract

Global average pooling (GAP) allows to localize discriminative information for recognition [40]. While GAP helps the convolution neural network to attend to the most discriminative features of an object, it may suffer if that information is missing e.g. due to camera viewpoint changes. To circumvent this issue, we argue that it is advantageous to attend to the global configuration of the object by modeling spatial relations among high-level features. We propose a novel architecture for Person Re-Identification, based on a novel parameter-free spatial attention layer introducing spatial relations among the feature map activations back to the model. Our spatial attention layer consistently improves the performance over the model without it. Results on four benchmarks demonstrate a superiority of our model over the state-of-the-art achieving rank-1 accuracy of 94.7% on Market-1501, 89.0% on DukeMTMC-ReID, 74.9% on CUHK03-labeled and 69.7% on CUHK03-detected.