UD-Gaussian: Uncertainty-Driven Gaussian Modeling for Occluded Person Re-Identification
- 16 March 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35 (10577149) , 2889-2900
Abstract
Occluded person re-identification aims to address the identification challenges posed by pedestrians obscured by other individuals or objects. Existing methods often rely on incorporating pose or semantic information to improve model performance under occlusion. However, such information often depends on external models with inevitably cross-domain gaps, whose stability is limited in complex occlusion environments and prone to false results. In this paper, we propose a Transformer-based uncertainty-driven Gaussian model, termed as UD-Gaussian. Firstly, to enrich the detailed features of pedestrian images, a high-frequency enhancement module is introduced. The high-frequency components of the pedestrian image are extracted by Discrete Haar Wavelet Transform, and Top-K high-frequency patches are extracted to construct a graph Laplacian matrix to achieve high-frequency graph attention, which is fused with features learned from self-attention to enhance the high-frequency feature representation. Given the uncertainty in pedestrian feature learning induced by occlusion makes it challenging to obtain reliable and stable pedestrian features, we propose a probability distribution learning module. This module establishes a memory bank to build Gaussian distributions for each pedestrian identity and the entropy is introduced as a loss function to encourage the model to generate more deterministic and relatively independent probability distributions, thereby enhancing the discriminative ability of the model across different pedestrian identities. The high-frequency enhancement module provides a solid foundation for the probability distribution learning module, alleviating uncertainty caused by pedestrian images themselves. Experimental results on occluded and holistic person re-identification datasets demonstrate the superiority of the proposed method.Keywords
Funding Information
- China Postdoctoral Science Foundation (2025M771518)
- National Key Research and Development Program of China (2022YFB3104700)
- National Natural Science Foundation of China (62376198)
- National Natural Science Foundation of China (62576247)
- Engineering Research Center of Big Data Intelligence
This publication has 62 references indexed in Scilit:
- TransMatch: Transformer-based correspondence pruning via local and global consensusPattern Recognition, 2024
- Multi-granularity Cross Transformer Network for person re-identificationPattern Recognition, 2024
- Multi-view Information Integration and Propagation for occluded person re-identificationInformation Fusion, 2023
- Person re-identification: A retrospective on domain specific open challenges and future trendsPattern Recognition, 2023
- Spatial-driven features based on image dependencies for person re-identificationPattern Recognition, 2022
- Identity-Guided Human Semantic Parsing for Person Re-identification2020
- SCPNet: Spatial-Channel Parallelism Network for Joint Holistic and Partial Person Re-identification2019
- Beyond Part Models: Person Retrieval with Refined Part Pooling (and A Strong Convolutional Baseline)2018
- Performance Measures and a Data Set for Multi-target, Multi-camera Tracking2016
- DeepReID: Deep Filter Pairing Neural Network for Person Re-identification2014