# Strength in Diversity: Multi-Branch Representation Learning for Vehicle Re-Identification

arXiv: https://arxiv.org/abs/2310.01129 · HTML: https://mlsanity.com/paper/2310.01129/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 34 references that are in the map.
- First posted on arXiv 2 Oct 2023.

## Builds on (most cited first, 19 of 19)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [In Defense of the Triplet Loss for Person Re-Identification](https://mlsanity.com/paper/1703.07737/) (2017)
- [TransReID: Transformer-based Object Re-Identification](https://mlsanity.com/paper/2102.04378/) (2021)
- [Bag of Tricks and A Strong Baseline for Deep Person Re-identification](https://mlsanity.com/paper/1903.07071/) (2019)
- [Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net](https://mlsanity.com/paper/1807.09441/) (2018)
- [Bottleneck Transformers for Visual Recognition](https://mlsanity.com/paper/2101.11605/) (2021)
- [Learning Discriminative Features with Multiple Granularities for Person Re-Identification](https://mlsanity.com/paper/1804.01438/) (2018)
- [Re-ranking Person Re-identification with k-reciprocal Encoding](https://mlsanity.com/paper/1701.08398/) (2017)
- [FastReID: A Pytorch Toolbox for General Instance Re-identification](https://mlsanity.com/paper/2006.02631/) (2020)
- [Parsing-based View-aware Embedding Network for Vehicle Re-Identification](https://mlsanity.com/paper/2004.05021/) (2020)
- [The Devil is in the Details: Self-Supervised Attention for Vehicle Re-Identification](https://mlsanity.com/paper/2004.06271/) (2020)
- [Self-supervised Geometric Features Discovery via Interpretable Attention for Vehicle Re-Identification and Beyond](https://mlsanity.com/paper/2010.09221/) (2020)
- [Heterogeneous Relational Complement for Vehicle Re-identification](https://mlsanity.com/paper/2109.07894/) (2021)
- [In Defense of the Classification Loss for Person Re-Identification](https://mlsanity.com/paper/1809.05864/) (2018)
- [Looking GLAMORous: Vehicle Re-Id in Heterogeneous Cameras Networks with Global and Local Attention](https://mlsanity.com/paper/2002.02256/) (2020)
- [AttributeNet: Attribute Enhanced Vehicle Re-Identification](https://mlsanity.com/paper/2102.03898/) (2021)

## Built on by (most cited first, 4 of 4)

- [CLIP-SENet: CLIP-based Semantic Enhancement Network for Vehicle Re-identification](https://mlsanity.com/paper/2502.16815/) (2025)
- [LKA-ReID:Vehicle Re-Identification with Large Kernel Attention](https://mlsanity.com/paper/2409.17908/) (2024)
- [CLIPVehicle: A Unified Framework for Vision-based Vehicle Search](https://mlsanity.com/paper/2508.04120/) (2025)
- [Rethinking Multi-Branch and Cross-Backbone Fusion for Vehicle Re-Identification under Foundation-Model Pretraining](https://mlsanity.com/paper/2607.22068/) (2026)

## Abstract (arXiv)

This paper presents an efficient and lightweight multi-branch deep architecture to improve vehicle re-identification (V-ReID). While most V-ReID work uses a combination of complex multi-branch architectures to extract robust and diversified embeddings towards re-identification, we advocate that simple and lightweight architectures can be designed to fulfill the Re-ID task without compromising performance. We propose a combination of Grouped-convolution and Loss-Branch-Split strategies to design a multi-branch architecture that improve feature diversity and feature discriminability. We combine a ResNet50 global branch architecture with a BotNet self-attention branch architecture, both designed within a Loss-Branch-Split (LBS) strategy. We argue that specialized loss-branch-splitting helps to improve re-identification tasks by generating specialized re-identification features. A lightweight solution using grouped convolution is also proposed to mimic the learning of loss-splitting into multiple embeddings while significantly reducing the model size. In addition, we designed an improved solution to leverage additional metadata, such as camera ID and pose information, that uses 97% less parameters, further improving re-identification performance. In comparison to state-of-the-art (SoTA) methods, our approach outperforms competing solutions in Veri-776 by achieving 85.6% mAP and 97.7% CMC1 and obtains competitive results in Veri-Wild with 88.1% mAP and 96.3% CMC1. Overall, our work provides important insights into improving vehicle re-identification and presents a strong basis for other retrieval tasks. Our code is available at the https://github.com/videturfortuna/vehicle_reid_itsc2023.