Homocentric Hypersphere Feature Embedding for Person Re-identification
arXiv:1804.08866
Abstract
Person re-identification (Person ReID) is a challenging task due to the large variations in camera viewpoint, lighting, resolution, and human pose. Recently, with the advancement of deep learning technologies, the performance of Person ReID has been improved swiftly. Feature extraction and feature matching are two crucial components in the training and deployment stages of Person ReID. However, many existing Person ReID methods have measure inconsistency between the training stage and the deployment stage, and they couple magnitude and orientation information of feature vectors in feature representation. Meanwhile, traditional triplet loss methods focus on samples within a mini-batch and lack knowledge of global feature distribution. To address these issues, we propose a novel homocentric hypersphere embedding scheme to decouple magnitude and orientation information for both feature and weight vectors, and reformulate classification loss and triplet loss to their angular versions and combine them into an angular discriminative loss. We evaluate our proposed method extensively on the widely used Person ReID benchmarks, including Market1501, CUHK03 and DukeMTMC-ReID. Our method demonstrates leading performance on all datasets.
arXiv comment11 pages, 7 figures
References in corpus (12)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- In Defense of the Triplet Loss for Person Re-Identification
- Person Re-identification: Past, Present and Future
- Improving Person Re-identification by Attribute and Identity Learning
- Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks
- Random Erasing Data Augmentation
- Pedestrian Alignment Network for Large-scale Person Re-identification
- Deep Transfer Learning for Person Re-identification
- PersonNet: Person Re-identification with Deep Convolutional Neural Networks
- Deep Metric Learning for Practical Person Re-Identification
- SVDNet for Pedestrian Retrieval
- All You Need is Beyond a Good Init: Exploring Better Solution for Training Extremely Deep Convolutional Neural Networks with Orthonormality and Modulation