# Unsupervised Noisy Tracklet Person Re-identification

arXiv: https://arxiv.org/abs/2101.06391 · HTML: https://mlsanity.com/paper/2101.06391/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 51 references that are in the map.
- First posted on arXiv 16 Jan 2021.

## Builds on (most cited first, 29 of 29)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018)
- [Focal Loss for Dense Object Detection](https://mlsanity.com/paper/1708.02002/) (2017)
- [Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking](https://mlsanity.com/paper/1609.01775/) (2016)
- [Deep Mutual Learning](https://mlsanity.com/paper/1706.00384/) (2017)
- [Person Transfer GAN to Bridge Domain Gap for Person Re-Identification](https://mlsanity.com/paper/1711.08565/) (2017)
- [Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro](https://mlsanity.com/paper/1701.07717/) (2017)
- [Harmonious Attention Network for Person Re-Identification](https://mlsanity.com/paper/1802.08122/) (2018)
- [Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification](https://mlsanity.com/paper/1711.07027/) (2017)
- [MOTChallenge 2015: Towards a Benchmark for Multi-Target Tracking](https://mlsanity.com/paper/1504.01942/) (2015)
- [Part-Aligned Bilinear Representations for Person Re-identification](https://mlsanity.com/paper/1804.07094/) (2018)
- [Unsupervised Person Re-identification: Clustering and Fine-tuning](https://mlsanity.com/paper/1705.10444/) (2017)
- [Transferable Joint Attribute-Identity Deep Learning for Unsupervised Person Re-Identification](https://mlsanity.com/paper/1803.09786/) (2018)
- [Multi-Level Factorisation Net for Person Re-Identification](https://mlsanity.com/paper/1803.09132/) (2018)
- [Unsupervised Tracklet Person Re-Identification](https://mlsanity.com/paper/1903.00535/) (2019)
- [Detect-and-Track: Efficient Pose Estimation in Videos](https://mlsanity.com/paper/1712.09184/) (2017)
- [Person Re-identification with Deep Similarity-Guided Graph Neural Network](https://mlsanity.com/paper/1807.09975/) (2018)
- [Unsupervised Person Re-identification by Deep Learning Tracklet Association](https://mlsanity.com/paper/1809.02874/) (2018)
- [Domain Adaptation through Synthesis for Unsupervised Person Re-identification](https://mlsanity.com/paper/1804.10094/) (2018)
- [Learning Deep Feature Representations with Domain Guided Dropout for Person Re-identification](https://mlsanity.com/paper/1604.07528/) (2016)
- [Person Re-Identification by Camera Correlation Aware Feature Augmentation](https://mlsanity.com/paper/1703.08837/) (2017)
- [Cross-view Asymmetric Metric Learning for Unsupervised Person Re-identification](https://mlsanity.com/paper/1708.08062/) (2017)
- [Dynamic Label Graph Matching for Unsupervised Video Re-Identification](https://mlsanity.com/paper/1709.09297/) (2017)
- [Human-In-The-Loop Person Re-Identification](https://mlsanity.com/paper/1612.01345/) (2016)
- [Deep Association Learning for Unsupervised Video Person Re-identification](https://mlsanity.com/paper/1808.07301/) (2018)
- [Person Re-Identification by Deep Joint Learning of Multi-Loss Classification](https://mlsanity.com/paper/1705.04724/) (2017)
- [Deep Group-shuffling Random Walk for Person Re-identification](https://mlsanity.com/paper/1807.11178/) (2018)
- [Person Re-Identification by Unsupervised Video Matching](https://mlsanity.com/paper/1611.08512/) (2016)

## Abstract (arXiv)

Existing person re-identification (re-id) methods mostly rely on supervised model learning from a large set of person identity labelled training data per domain. This limits their scalability and usability in large scale deployments. In this work, we present a novel selective tracklet learning (STL) approach that can train discriminative person re-id models from unlabelled tracklet data in an unsupervised manner. This avoids the tedious and costly process of exhaustively labelling person image/tracklet true matching pairs across camera views. Importantly, our method is particularly more robust against arbitrary noisy data of raw tracklets therefore scalable to learning discriminative models from unconstrained tracking data. This differs from a handful of existing alternative methods that often assume the existence of true matches and balanced tracklet samples per identity class. This is achieved by formulating a data adaptive image-to-tracklet selective matching loss function explored in a multi-camera multi-task deep learning model structure. Extensive comparative experiments demonstrate that the proposed STL model surpasses significantly the state-of-the-art unsupervised learning and one-shot learning re-id methods on three large tracklet person re-id benchmarks.