LEViT: Locally Enhanced Vision Transformer for Efficient Object Re-Identification
- 18 December 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28 (15209210) , 1820-1832
Abstract
Vision Transformer (ViT) on object re-identification (ReID) has attracted significant attention recently. However, ViT-based ReID substantially increases computational complexity, imposing significant burdens during training and inference. This paper presents an efficient and effective ViT-based backbone for ReID tasks, called the Locally Enhanced Vision Transformer (LEViT). ViT models typically emphasize global relationship modeling, yet ReID tasks are more sensitive to local information. To address this gap, we propose a Locally Enhanced (LE) block to enhance local information by performing self-attention within local split windows. Since part-based models dominate ReID, calculating self-attention across all patches is computationally inefficient. We also replace the traditional Query-Key-Value projector with the Group Convolution (G-Conv) projector, enabling the model to capture local details more efficiently. Furthermore, G-Conv is integrated into the channel MLP to strengthen local feature sensitivity. Using these components, we develop two LEViT variants: LEViT-S and LEViT-L. To our knowledge, LEViT is the first highly adaptable ViT backbone for ReID tasks. Experimental evaluations demonstrate the effectiveness in five ReID datasets: Market1501, DukeMTMC, MSMT17, VeRi-776, and VehicleID. Notably, LEViT-S outperforms TransReID while requiring less than 10% computational complexity. Furthermore, LEViT obtains the state-of-the-art on three deep metric learning datasets: CUB-200-2011, Cars196, and University-1652. Our code will be available at https://github.com/YuhuiWang99/LEViT.Keywords
Funding Information
- National Natural Science Foundation of China (62273301)
- National Natural Science Foundation of China (62273302)
- National Natural Science Foundation of China (62302140)
- Fundamental Research Funds for the Central Universities (JZ2024HGTB0261)
This publication has 108 references indexed in Scilit:
- Efficient Vision Transformers with Partial Attention2024
- What Limits the Performance of Local Self-attention?International Journal of Computer Vision, 2023
- Identity-Guided Human Semantic Parsing for Person Re-identification2020
- The Devil Is in the Details: Self-supervised Attention for Vehicle Re-identification2020
- DiVA: Diverse Visual Feature Aggregation for Deep Metric Learning2020
- End-to-End Object Detection with Transformers2020
- ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design2018
- Part-Aligned Bilinear Representations for Person Re-identification2018
- 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