# Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro

arXiv: https://arxiv.org/abs/1701.07717 · HTML: https://mlsanity.com/paper/1701.07717/

## Key facts

- Cited by 281 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Jan 2017.

## Built on by (most cited first, 30 of 281)

- [Domain Generalization: A Survey](https://mlsanity.com/paper/2103.02503/) (2021)
- [Domain Generalization with MixStyle](https://mlsanity.com/paper/2104.02008/) (2021)
- [Effective Data Augmentation With Diffusion Models](https://mlsanity.com/paper/2302.07944/) (2023)
- [Diverse Part Discovery: Occluded Person Re-identification with Part-Aware Transformer](https://mlsanity.com/paper/2106.04095/) (2021)
- [Generalizable Person Re-identification with Relevance-aware Mixture of Experts](https://mlsanity.com/paper/2105.09156/) (2021)
- [Towards Unified Text-based Person Retrieval: A Large-scale Multi-Attribute and Language Search Benchmark](https://mlsanity.com/paper/2306.02898/) (2023)
- [Pose-guided Feature Disentangling for Occluded Person Re-identification Based on Transformer](https://mlsanity.com/paper/2112.02466/) (2021)
- [MixStyle Neural Networks for Domain Generalization and Adaptation](https://mlsanity.com/paper/2107.02053/) (2021)
- [Body Part-Based Representation Learning for Occluded Person Re-Identification](https://mlsanity.com/paper/2211.03679/) (2022)
- [Lifelong Person Re-Identification via Adaptive Knowledge Accumulation](https://mlsanity.com/paper/2103.12462/) (2021)
- [NFormer: Robust Person Re-identification with Neighbor Transformer](https://mlsanity.com/paper/2204.09331/) (2022)
- [Person Re-identification Method Based on Color Attack and Joint Defence](https://mlsanity.com/paper/2111.09571/) (2021)
- [Recent Advances of Continual Learning in Computer Vision: An Overview](https://mlsanity.com/paper/2109.11369/) (2021)
- [IDM: An Intermediate Domain Module for Domain Adaptive Person Re-ID](https://mlsanity.com/paper/2108.02413/) (2021)
- [GiT: Graph Interactive Transformer for Vehicle Re-identification](https://mlsanity.com/paper/2107.05475/) (2021)
- [Mitigating Dataset Harms Requires Stewardship: Lessons from 1000 Papers](https://mlsanity.com/paper/2108.02922/) (2021)
- [PLIP: Language-Image Pre-training for Person Representation Learning](https://mlsanity.com/paper/2305.08386/) (2023)
- [AAformer: Auto-Aligned Transformer for Person Re-Identification](https://mlsanity.com/paper/2104.00921/) (2021)
- [Large-Scale Spatio-Temporal Person Re-identification: Algorithms and Benchmark](https://mlsanity.com/paper/2105.15076/) (2021)
- [Instruct-ReID: A Multi-purpose Person Re-identification Task with Instructions](https://mlsanity.com/paper/2306.07520/) (2023)
- [Cross Attention Based Style Distribution for Controllable Person Image Synthesis](https://mlsanity.com/paper/2208.00712/) (2022)
- [Learning Disentangled Representation Implicitly via Transformer for Occluded Person Re-Identification](https://mlsanity.com/paper/2107.02380/) (2021)
- [Deep Frequency Filtering for Domain Generalization](https://mlsanity.com/paper/2203.12198/) (2022)
- [Eliminate Deviation with Deviation for Data Augmentation and a General Multi-modal Data Learning Method](https://mlsanity.com/paper/2101.08533/) (2021)
- [Anchor-Free Person Search](https://mlsanity.com/paper/2103.11617/) (2021)
- [Feature Erasing and Diffusion Network for Occluded Person Re-Identification](https://mlsanity.com/paper/2112.08740/) (2021)
- [Large-Scale Pre-training for Person Re-identification with Noisy Labels](https://mlsanity.com/paper/2203.16533/) (2022)
- [HAT: Hierarchical Aggregation Transformers for Person Re-identification](https://mlsanity.com/paper/2107.05946/) (2021)
- [CM-NAS: Cross-Modality Neural Architecture Search for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2101.08467/) (2021)
- [Multiple-environment Self-adaptive Network for Aerial-view Geo-localization](https://mlsanity.com/paper/2204.08381/) (2022)

## Abstract (arXiv)

The main contribution of this paper is a simple semi-supervised pipeline that only uses the original training set without collecting extra data. It is challenging in 1) how to obtain more training data only from the training set and 2) how to use the newly generated data. In this work, the generative adversarial network (GAN) is used to generate unlabeled samples. We propose the label smoothing regularization for outliers (LSRO). This method assigns a uniform label distribution to the unlabeled images, which regularizes the supervised model and improves the baseline. We verify the proposed method on a practical problem: person re-identification (re-ID). This task aims to retrieve a query person from other cameras. We adopt the deep convolutional generative adversarial network (DCGAN) for sample generation, and a baseline convolutional neural network (CNN) for representation learning. Experiments show that adding the GAN-generated data effectively improves the discriminative ability of learned CNN embeddings. On three large-scale datasets, Market-1501, CUHK03 and DukeMTMC-reID, we obtain +4.37%, +1.6% and +2.46% improvement in rank-1 precision over the baseline CNN, respectively. We additionally apply the proposed method to fine-grained bird recognition and achieve a +0.6% improvement over a strong baseline. The code is available at https://github.com/layumi/Person-reID_GAN.