Group Consistent Similarity Learning via Deep CRF for Person Re-identification

Citations Over TimeTop 1% of 2018 papers

Abstract

Person re-identification benefits greatly from deep neural networks (DNN) to learn accurate similarity metrics and robust feature embeddings. However, most of the current methods impose only local constraints for similarity learning. In this paper, we incorporate constraints on large image groups by combining the CRF with deep neural networks. The proposed method aims to learn the "local similarity" metrics for image pairs while taking into account the dependencies from all the images in a group, forming "group similarities". Our method involves multiple images to model the relationships among the local and global similarities in a unified CRF during training, while combines multi-scale local similarities as the predicted similarity in testing. We adopt an approximate inference scheme for estimating the group similarity, enabling end-to-end training. Extensive experiments demonstrate the effectiveness of our model that combines DNN and CRF for learning robust multi-scale local similarities. The overall results outperform those by state-of-the-arts with considerable margins on three widely-used benchmarks.

Related Papers

• → Medical Image Analysis With Deep Neural Networks(2019)29 cited
• → Similarity Learning For Cover Song Identification Using Cross-Similarity Matrices of Multi-Level Deep Sequences(2020)16 cited
• → Measuring Patient Similarity on Multiple Diseases by Joint Learning via a Convolutional Neural Network(2021)7 cited
• → A Deep Representation Learning Framework for Medical Imaging Data Analysis(2020)1 cited
• → Similarity learning based on extension logic(2004)