Spectral Feature Transformation for Person Re-identification

Abstract

With the surge of deep learning techniques, the field of person re-identification has witnessed rapid progress in recent years. Deep learning based methods focus on learning a feature space where samples are clustered compactly according to their corresponding identities. Most existing methods rely on powerful CNNs to transform the samples individually. In contrast, we propose to consider the sample relations in the transformation. To achieve this goal, we incorporate spectral clustering technique into CNN. We derive a novel module named Spectral Feature Transformation and seamlessly integrate it into existing CNN pipeline with negligible cost,which makes our method enjoy the best of two worlds. Empirical studies show that the proposed approach outperforms previous state-of-the-art methods on four public benchmarks by a considerable margin without bells and whistles.

arXiv commentTech Report

References in corpus (17)

• Deep Residual Learning for Image Recognition
• Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
• MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems
• Improving Person Re-identification by Attribute and Identity Learning
• Random Erasing Data Augmentation
• Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition
• Large-Margin Softmax Loss for Convolutional Neural Networks
• GLAD: Global-Local-Alignment Descriptor for Pedestrian Retrieval
• SphereFace: Deep Hypersphere Embedding for Face Recognition
• CosFace: Large Margin Cosine Loss for Deep Face Recognition
• Non-local Neural Networks
• SVDNet for Pedestrian Retrieval
• SpectralNet: Spectral Clustering using Deep Neural Networks
• Normalized Cut Loss for Weakly-supervised CNN Segmentation
• Disentangled Person Image Generation
• Improving Generalization via Scalable Neighborhood Component Analysis
• Deep clustering: Discriminative embeddings for segmentation and separation