# Rethinking Person Re-Identification via Semantic-Based Pretraining

arXiv: https://arxiv.org/abs/2110.05074 · HTML: https://mlsanity.com/paper/2110.05074/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 59 references that are in the map.
- First posted on arXiv 11 Oct 2021.

## Builds on (most cited first, 30 of 40)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels](https://mlsanity.com/paper/1805.07836/) (2018)
- [In Defense of the Triplet Loss for Person Re-Identification](https://mlsanity.com/paper/1703.07737/) (2017)
- [Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking](https://mlsanity.com/paper/1609.01775/) (2016)
- [Person Transfer GAN to Bridge Domain Gap for Person Re-Identification](https://mlsanity.com/paper/1711.08565/) (2017)
- [Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)](https://mlsanity.com/paper/1711.09349/) (2017)
- [Bag of Tricks and A Strong Baseline for Deep Person Re-identification](https://mlsanity.com/paper/1903.07071/) (2019)
- [Circle Loss: A Unified Perspective of Pair Similarity Optimization](https://mlsanity.com/paper/2002.10857/) (2020)
- [Rethinking ImageNet Pre-training](https://mlsanity.com/paper/1811.08883/) (2018)
- [Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net](https://mlsanity.com/paper/1807.09441/) (2018)
- [VirTex: Learning Visual Representations from Textual Annotations](https://mlsanity.com/paper/2006.06666/) (2020)
- [Lookahead Optimizer: k steps forward, 1 step back](https://mlsanity.com/paper/1907.08610/) (2019)
- [Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro](https://mlsanity.com/paper/1701.07717/) (2017)
- [Re-ranking Person Re-identification with k-reciprocal Encoding](https://mlsanity.com/paper/1701.08398/) (2017)
- [Joint Discriminative and Generative Learning for Person Re-identification](https://mlsanity.com/paper/1904.07223/) (2019)
- [Eigen-CAM: Class Activation Map using Principal Components](https://mlsanity.com/paper/2008.00299/) (2020)
- [Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification](https://mlsanity.com/paper/1711.07027/) (2017)
- [Improving Person Re-identification by Attribute and Identity Learning](https://mlsanity.com/paper/1703.07220/) (2017)
- [Unsupervised Pre-training for Person Re-identification](https://mlsanity.com/paper/2012.03753/) (2020)
- [Hierarchical Clustering with Hard-batch Triplet Loss for Person Re-identification](https://mlsanity.com/paper/1910.12278/) (2019)
- [FD-GAN: Pose-guided Feature Distilling GAN for Robust Person Re-identification](https://mlsanity.com/paper/1810.02936/) (2018)
- [Pose-Normalized Image Generation for Person Re-identification](https://mlsanity.com/paper/1712.02225/) (2017)
- [Mixed High-Order Attention Network for Person Re-Identification](https://mlsanity.com/paper/1908.05819/) (2019)
- [SVDNet for Pedestrian Retrieval](https://mlsanity.com/paper/1703.05693/) (2017)
- [Semantic-Aware Scene Recognition](https://mlsanity.com/paper/1909.02410/) (2019)

## Built on by (most cited first, 6 of 6)

- [VM-UNet: Vision Mamba UNet for Medical Image Segmentation](https://mlsanity.com/paper/2402.02491/) (2024)
- [Learning Multi-axis Representation in Frequency Domain for Medical Image Segmentation](https://mlsanity.com/paper/2312.17030/) (2023)
- [Deep Multimodal Fusion for Generalizable Person Re-identification](https://mlsanity.com/paper/2211.00933/) (2022)
- [Learning Collaborative Knowledge with Multimodal Representation for Polyp Re-Identification](https://mlsanity.com/paper/2408.05914/) (2024)
- [Hand Held Multi-Object Tracking Dataset in American Football](https://mlsanity.com/paper/2511.09455/) (2025)
- [GPF-Net: Gated Progressive Fusion Learning for Polyp Re-Identification](https://mlsanity.com/paper/2512.21476/) (2025)

## Abstract (arXiv)

Pretraining is a dominant paradigm in computer vision. Generally, supervised ImageNet pretraining is commonly used to initialize the backbones of person re-identification (Re-ID) models. However, recent works show a surprising result that CNN-based pretraining on ImageNet has limited impacts on Re-ID system due to the large domain gap between ImageNet and person Re-ID data. To seek an alternative to traditional pretraining, here we investigate semantic-based pretraining as another method to utilize additional textual data against ImageNet pretraining. Specifically, we manually construct a diversified FineGPR-C caption dataset for the first time on person Re-ID events. Based on it, a pure semantic-based pretraining approach named VTBR is proposed to adopt dense captions to learn visual representations with fewer images. We train convolutional neural networks from scratch on the captions of FineGPR-C dataset, and then transfer them to downstream Re-ID tasks. Comprehensive experiments conducted on benchmark datasets show that our VTBR can achieve competitive performance compared with ImageNet pretraining - despite using up to 1.4x fewer images, revealing its potential in Re-ID pretraining.