An Enhanced Deep Feature Representation for Person Re-identification
This work addresses feature representation for person re-identification, offering an incremental improvement by fusing existing feature types.
The paper tackles the problem of person re-identification by proposing a feature extraction model that combines CNN features with hand-crafted histogram features, resulting in improved discriminative and compact representations validated on three datasets.
Feature representation and metric learning are two critical components in person re-identification models. In this paper, we focus on the feature representation and claim that hand-crafted histogram features can be complementary to Convolutional Neural Network (CNN) features. We propose a novel feature extraction model called Feature Fusion Net (FFN) for pedestrian image representation. In FFN, back propagation makes CNN features constrained by the handcrafted features. Utilizing color histogram features (RGB, HSV, YCbCr, Lab and YIQ) and texture features (multi-scale and multi-orientation Gabor features), we get a new deep feature representation that is more discriminative and compact. Experiments on three challenging datasets (VIPeR, CUHK01, PRID450s) validates the effectiveness of our proposal.