In Defense of the Classification Loss for Person Re-Identification
arXiv:1809.05864
Abstract
The recent research for person re-identification has been focused on two trends. One is learning the part-based local features to form more informative feature descriptors. The other is designing effective metric learning loss functions such as the triplet loss family. We argue that learning global features with classification loss could achieve the same goal, even with some simple and cost-effective architecture design. In this paper, we first explain why the person re-id framework with standard classification loss usually has inferior performance compared to metric learning. Based on that, we further propose a person re-id framework featured by channel grouping and multi-branch strategy, which divides global features into multiple channel groups and learns the discriminative channel group features by multi-branch classification layers. The extensive experiments show that our framework outperforms prior state-of-the-arts in terms of both accuracy and inference speed.
References in corpus (19)
- Deep Residual Learning for Image Recognition
- R-FCN: Object Detection via Region-based Fully Convolutional Networks
- In Defense of the Triplet Loss for Person Re-Identification
- Going Deeper with Convolutions
- Person Re-identification: Past, Present and Future
- Random Erasing Data Augmentation
- Pedestrian Alignment Network for Large-scale Person Re-identification
- Deep Representation Learning with Part Loss for Person Re-Identification
- AlignedReID: Surpassing Human-Level Performance in Person Re-Identification
- GLAD: Global-Local-Alignment Descriptor for Pedestrian Retrieval
- Deep Transfer Learning for Person Re-identification
- PersonNet: Person Re-identification with Deep Convolutional Neural Networks
- Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro
- Pose Invariant Embedding for Deep Person Re-identification
- Deeply-Learned Part-Aligned Representations for Person Re-Identification
- Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)
- HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis
- Deep Mutual Learning
- Person Re-Identification by Deep Joint Learning of Multi-Loss Classification