# Adaptive Exploration for Unsupervised Person Re-Identification

arXiv: https://arxiv.org/abs/1907.04194 · HTML: https://mlsanity.com/paper/1907.04194/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Jul 2019.

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

- [Mixing Up Contrastive Learning: Self-Supervised Representation Learning for Time Series](https://mlsanity.com/paper/2203.09270/) (2022)
- [IDM: An Intermediate Domain Module for Domain Adaptive Person Re-ID](https://mlsanity.com/paper/2108.02413/) (2021)
- [Joint Noise-Tolerant Learning and Meta Camera Shift Adaptation for Unsupervised Person Re-Identification](https://mlsanity.com/paper/2103.04618/) (2021)
- [Triplet Contrastive Representation Learning for Unsupervised Vehicle Re-identification](https://mlsanity.com/paper/2301.09498/) (2023)
- [MLNet: Mutual Learning Network with Neighborhood Invariance for Universal Domain Adaptation](https://mlsanity.com/paper/2312.07871/) (2023)
- [Adaptive Boosting for Domain Adaptation: Towards Robust Predictions in Scene Segmentation](https://mlsanity.com/paper/2103.15685/) (2021)
- [Self-supervised Point Cloud Representation Learning via Separating Mixed Shapes](https://mlsanity.com/paper/2109.00452/) (2021)
- [Meta Clustering Learning for Large-scale Unsupervised Person Re-identification](https://mlsanity.com/paper/2111.10032/) (2021)
- [Unsupervised Vehicle Re-Identification via Self-supervised Metric Learning using Feature Dictionary](https://mlsanity.com/paper/2103.02250/) (2021)
- [Domain-Class Correlation Decomposition for Generalizable Person Re-Identification](https://mlsanity.com/paper/2106.15206/) (2021)
- [Camera-Tracklet-Aware Contrastive Learning for Unsupervised Vehicle Re-Identification](https://mlsanity.com/paper/2109.06401/) (2021)
- [Bridging the Source-to-target Gap for Cross-domain Person Re-Identification with Intermediate Domains](https://mlsanity.com/paper/2203.01682/) (2022)
- [Style Variable and Irrelevant Learning for Generalizable Person Re-identification](https://mlsanity.com/paper/2209.05235/) (2022)
- [Unsupervised Domain Adaptation Network with Category-Centric Prototype Aligner for Biomedical Image Segmentation](https://mlsanity.com/paper/2103.02220/) (2021)
- [Fast One-Stage Unsupervised Domain Adaptive Person Search](https://mlsanity.com/paper/2405.02832/) (2024)
- [Boosting Cross-Domain Point Classification via Distilling Relational Priors from 2D Transformers](https://mlsanity.com/paper/2407.18534/) (2024)
- [CORE-ReID V2: Advancing the Domain Adaptation for Object Re-Identification with Optimized Training and Ensemble Fusion](https://mlsanity.com/paper/2508.04036/) (2025)

## Abstract (arXiv)

Due to domain bias, directly deploying a deep person re-identification (re-ID) model trained on one dataset often achieves considerably poor accuracy on another dataset. In this paper, we propose an Adaptive Exploration (AE) method to address the domain-shift problem for re-ID in an unsupervised manner. Specifically, in the target domain, the re-ID model is inducted to 1) maximize distances between all person images and 2) minimize distances between similar person images. In the first case, by treating each person image as an individual class, a non-parametric classifier with a feature memory is exploited to encourage person images to move far away from each other. In the second case, according to a similarity threshold, our method adaptively selects neighborhoods for each person image in the feature space. By treating these similar person images as the same class, the non-parametric classifier forces them to stay closer. However, a problem of the adaptive selection is that, when an image has too many neighborhoods, it is more likely to attract other images as its neighborhoods. As a result, a minority of images may select a large number of neighborhoods while a majority of images have only a few neighborhoods. To address this issue, we additionally integrate a balance strategy into the adaptive selection. We evaluate our methods with two protocols. The first one is called "target-only re-ID", in which only the unlabeled target data is used for training. The second one is called "domain adaptive re-ID", in which both the source data and the target data are used during training. Experimental results on large-scale re-ID datasets demonstrate the effectiveness of our method. Our code has been released at https://github.com/dyh127/Adaptive-Exploration-for-Unsupervised-Person-Re-Identification.