DeepAI AI Chat
Log In Sign Up

Let Features Decide for Themselves: Feature Mask Network for Person Re-identification

by   Guodong Ding, et al.
Australian National University

Person re-identification aims at establishing the identity of a pedestrian from a gallery that contains images of multiple people obtained from a multi-camera system. Many challenges such as occlusions, drastic lighting and pose variations across the camera views, indiscriminate visual appearances, cluttered backgrounds, imperfect detections, motion blur, and noise make this task highly challenging. While most approaches focus on learning features and metrics to derive better representations, we hypothesize that both local and global contextual cues are crucial for an accurate identity matching. To this end, we propose a Feature Mask Network (FMN) that takes advantage of ResNet high-level features to predict a feature map mask and then imposes it on the low-level features to dynamically reweight different object parts for a locally aware feature representation. This serves as an effective attention mechanism by allowing the network to focus on local details selectively. Given the resemblance of person re-identification with classification and retrieval tasks, we frame the network training as a multi-task objective optimization, which further improves the learned feature descriptions. We conduct experiments on Market-1501, DukeMTMC-reID and CUHK03 datasets, where the proposed approach respectively achieves significant improvements of 5.3%, 9.1% and 10.7% in mAP measure relative to the state-of-the-art.


page 1

page 3

page 6

page 8


End-to-End Comparative Attention Networks for Person Re-identification

Person re-identification across disjoint camera views has been widely ap...

Hand-Based Person Identification using Global and Part-Aware Deep Feature Representation Learning

In cases of serious crime, including sexual abuse, often the only availa...

Cross-Camera Feature Prediction for Intra-Camera Supervised Person Re-identification across Distant Scenes

Person re-identification (Re-ID) aims to match person images across non-...

Exploiting Robust Unsupervised Video Person Re-identification

Unsupervised video person re-identification (reID) methods usually depen...

Learning Invariant Color Features for Person Re-Identification

Matching people across multiple camera views known as person re-identifi...

Discovering Underlying Person Structure Pattern with Relative Local Distance for Person Re-identification

Modeling the underlying person structure for person re-identification (r...

Multi-Resolution Overlapping Stripes Network for Person Re-Identification

This paper addresses the person re-identification (PReID) problem by com...