Learning Discriminative Features with Multiple Granularities for Person Re-Identification
arXiv:1804.01438 · doi:10.1145/3240508.3240552
Abstract
The combination of global and partial features has been an essential solution to improve discriminative performances in person re-identification (Re-ID) tasks. Previous part-based methods mainly focus on locating regions with specific pre-defined semantics to learn local representations, which increases learning difficulty but not efficient or robust to scenarios with large variances. In this paper, we propose an end-to-end feature learning strategy integrating discriminative information with various granularities. We carefully design the Multiple Granularity Network (MGN), a multi-branch deep network architecture consisting of one branch for global feature representations and two branches for local feature representations. Instead of learning on semantic regions, we uniformly partition the images into several stripes, and vary the number of parts in different local branches to obtain local feature representations with multiple granularities. Comprehensive experiments implemented on the mainstream evaluation datasets including Market-1501, DukeMTMC-reid and CUHK03 indicate that our method has robustly achieved state-of-the-art performances and outperformed any existing approaches by a large margin. For example, on Market-1501 dataset in single query mode, we achieve a state-of-the-art result of Rank-1/mAP=96.6%/94.2% after re-ranking.
9 pages, 5 figures. To appear in ACM Multimedia 2018
References in corpus (2)
Cited by in corpus (60)
- Parameter Sharing Exploration and Hetero-Center based Triplet Loss for Visible-Thermal Person Re-Identification
- A Transformer-Based Feature Segmentation and Region Alignment Method For UAV-View Geo-Localization
- MHSA-Net: Multi-Head Self-Attention Network for Occluded Person Re-Identification
- Interpretable and Generalizable Person Re-Identification with Query-Adaptive Convolution and Temporal Lifting
- Person Re-identification via Attention Pyramid
- Person Re-identification in Aerial Imagery
- CMTR: Cross-modality Transformer for Visible-infrared Person Re-identification
- Multi-task Learning with Coarse Priors for Robust Part-aware Person Re-identification
- Learning Feature Recovery Transformer for Occluded Person Re-identification
- Semantic-guided Pixel Sampling for Cloth-Changing Person Re-identification
- Learning to Purification for Unsupervised Person Re-identification
- SCAN: Self-and-Collaborative Attention Network for Video Person Re-identification
- Parameter-Efficient Person Re-identification in the 3D Space
- Lightweight Multi-Branch Network for Person Re-Identification
- Multi-Domain Adversarial Feature Generalization for Person Re-Identification
- Bi-directional Exponential Angular Triplet Loss for RGB-Infrared Person Re-Identification
- Deep Joint Source-Channel Coding for Wireless Image Retrieval
- Towards Homogeneous Modality Learning and Multi-Granularity Information Exploration for Visible-Infrared Person Re-Identification
- DeepSportradar-v1: Computer Vision Dataset for Sports Understanding with High Quality Annotations
- Joint Person Objectness and Repulsion for Person Search
- MSCMNet: Multi-scale Semantic Correlation Mining for Visible-Infrared Person Re-Identification
- Exploring Fine-Grained Representation and Recomposition for Cloth-Changing Person Re-Identification
- Joint Optimization in Edge-Cloud Continuum for Federated Unsupervised Person Re-identification
- Aligning Correlation Information for Domain Adaptation in Action Recognition
- Disentangled Representations for Short-Term and Long-Term Person Re-Identification
- Exploiting Robust Unsupervised Video Person Re-identification
- CDPM: Convolutional Deformable Part Models for Semantically Aligned Person Re-identification
- Leaning Compact and Representative Features for Cross-Modality Person Re-Identification
- Batch Coherence-Driven Network for Part-aware Person Re-Identification
- Cross-Camera Feature Prediction for Intra-Camera Supervised Person Re-identification across Distant Scenes
- Receptive Multi-granularity Representation for Person Re-Identification
- Optimizing Performance of Federated Person Re-identification: Benchmarking and Analysis
- ES-Net: Erasing Salient Parts to Learn More in Re-Identification
- Sampling Agnostic Feature Representation for Long-Term Person Re-identification
- MGH: Metadata Guided Hypergraph Modeling for Unsupervised Person Re-identification
- A review of Recent Techniques for Person Re-Identification
- Exploring the Quality of GAN Generated Images for Person Re-Identification
- Learnable Privacy-Preserving Anonymization for Pedestrian Images
- Ground-to-Aerial Person Search: Benchmark Dataset and Approach
- Exploring Shape Embedding for Cloth-Changing Person Re-Identification via 2D-3D Correspondences
- A heterogeneous branch and multi-level classification network for person re-identification
- Dual-Refinement: Joint Label and Feature Refinement for Unsupervised Domain Adaptive Person Re-Identification
- Building Computationally Efficient and Well-Generalizing Person Re-Identification Models with Metric Learning
- Improving Person Re-identification with Iterative Impression Aggregation
- Compact Network Training for Person ReID
- Unsupervised clothing change adaptive person ReID
- Content and Salient Semantics Collaboration for Cloth-Changing Person Re-Identification
- Unleashing the Potential of Pre-Trained Diffusion Models for Generalizable Person Re-Identification
- MMFL-Net: Multi-scale and Multi-granularity Feature Learning for Cross-domain Fashion Retrieval
- Grafted network for person re-identification
- Cerberus: Attribute-based person re-identification using semantic IDs
- Distribution Aligned Semantics Adaption for Lifelong Person Re-Identification
- Cross-Camera Trajectories Help Person Retrieval in a Camera Network
- Image-Text-Image Knowledge Transfer for Lifelong Person Re-Identification with Hybrid Clothing States
- TAL: Two-stream Adaptive Learning for Generalizable Person Re-identification
- Visual Person Understanding through Multi-Task and Multi-Dataset Learning
- An Empirical Study of Person Re-Identification with Attributes
- Diverse Deep Feature Ensemble Learning for Omni-Domain Generalized Person Re-identification
- Aligned Divergent Pathways for Omni-Domain Generalized Person Re-Identification
- Multi-Grained Vision-Language Alignment for Domain Generalized Person Re-Identification