# DomainMix: Learning Generalizable Person Re-Identification Without Human Annotations

arXiv: https://arxiv.org/abs/2011.11953 · HTML: https://mlsanity.com/paper/2011.11953/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Nov 2020.

## Built on by (most cited first, 17 of 17)

- [Generalizing to Unseen Domains: A Survey on Domain Generalization](https://mlsanity.com/paper/2103.03097/) (2021)
- [Adversarial Alignment for Source Free Object Detection](https://mlsanity.com/paper/2301.04265/) (2023)
- [AADG: Automatic Augmentation for Domain Generalization on Retinal Image Segmentation](https://mlsanity.com/paper/2207.13249/) (2022)
- [On the benefits of representation regularization in invariance based domain generalization](https://mlsanity.com/paper/2105.14529/) (2021)
- [Bag of Tricks and A Strong baseline for Image Copy Detection](https://mlsanity.com/paper/2111.08004/) (2021)
- [Identity-Seeking Self-Supervised Representation Learning for Generalizable Person Re-identification](https://mlsanity.com/paper/2308.08887/) (2023)
- [Domain Generalization in Machine Learning Models for Wireless Communications: Concepts, State-of-the-Art, and Open Issues](https://mlsanity.com/paper/2303.08106/) (2023)
- [Generalizable Person Re-identification via Balancing Alignment and Uniformity](https://mlsanity.com/paper/2411.11471/) (2024)
- [D2LV: A Data-Driven and Local-Verification Approach for Image Copy Detection](https://mlsanity.com/paper/2111.07090/) (2021)
- [Few-shot Adaptive Object Detection with Cross-Domain CutMix](https://mlsanity.com/paper/2208.14586/) (2022)
- [Learning Fair Invariant Representations under Covariate and Correlation Shifts Simultaneously](https://mlsanity.com/paper/2408.09312/) (2024)
- [ShiftKD: Benchmarking Knowledge Distillation under Distribution Shift](https://mlsanity.com/paper/2312.16242/) (2023)
- [FedCCRL: Federated Domain Generalization with Cross-Client Representation Learning](https://mlsanity.com/paper/2410.11267/) (2024)
- [Group-wise Scaling and Orthogonal Decomposition for Domain-Invariant Feature Extraction in Face Anti-Spoofing](https://mlsanity.com/paper/2507.04006/) (2025)
- [iBARLE: imBalance-Aware Room Layout Estimation](https://mlsanity.com/paper/2308.15050/) (2023)
- [Unity in Diversity: Multi-expert Knowledge Confrontation and Collaboration for Generalizable Vehicle Re-identification](https://mlsanity.com/paper/2407.07351/) (2024)
- [Semantic Data Augmentation Enhanced Invariant Risk Minimization for Medical Image Domain Generalization](https://mlsanity.com/paper/2502.05593/) (2025)

## Abstract (arXiv)

Existing person re-identification models often have low generalizability, which is mostly due to limited availability of large-scale labeled data in training. However, labeling large-scale training data is very expensive and time-consuming, while large-scale synthetic dataset shows promising value in learning generalizable person re-identification models. Therefore, in this paper a novel and practical person re-identification task is proposed,i.e. how to use labeled synthetic dataset and unlabeled real-world dataset to train a universal model. In this way, human annotations are no longer required, and it is scalable to large and diverse real-world datasets. To address the task, we introduce a framework with high generalizability, namely DomainMix. Specifically, the proposed method firstly clusters the unlabeled real-world images and selects the reliable clusters. During training, to address the large domain gap between two domains, a domain-invariant feature learning method is proposed, which introduces a new loss,i.e. domain balance loss, to conduct an adversarial learning between domain-invariant feature learning and domain discrimination, and meanwhile learns a discriminative feature for person re-identification. This way, the domain gap between synthetic and real-world data is much reduced, and the learned feature is generalizable thanks to the large-scale and diverse training data. Experimental results show that the proposed annotation-free method is more or less comparable to the counterpart trained with full human annotations, which is quite promising. In addition, it achieves the current state of the art on several person re-identification datasets under direct cross-dataset evaluation.