Online Unsupervised Domain Adaptation for Person Re-identification
- URL: http://arxiv.org/abs/2205.04383v1
- Date: Mon, 9 May 2022 15:36:08 GMT
- Title: Online Unsupervised Domain Adaptation for Person Re-identification
- Authors: Hamza Rami, Matthieu Ospici, St\'ephane Lathuili\`ere
- Abstract summary: We present a new yet practical online setting for Unsupervised Domain Adaptation for person Re-ID.
We adapt and evaluate the state-of-the-art UDA algorithms on this new online setting using the well-known Market-1501, Duke, and MSMT17 benchmarks.
- Score: 4.48123023008698
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Unsupervised domain adaptation for person re-identification (Person Re-ID) is
the task of transferring the learned knowledge on the labeled source domain to
the unlabeled target domain. Most of the recent papers that address this
problem adopt an offline training setting. More precisely, the training of the
Re-ID model is done assuming that we have access to the complete training
target domain data set. In this paper, we argue that the target domain
generally consists of a stream of data in a practical real-world application,
where data is continuously increasing from the different network's cameras. The
Re-ID solutions are also constrained by confidentiality regulations stating
that the collected data can be stored for only a limited period, hence the
model can no longer get access to previously seen target images. Therefore, we
present a new yet practical online setting for Unsupervised Domain Adaptation
for person Re-ID with two main constraints: Online Adaptation and Privacy
Protection. We then adapt and evaluate the state-of-the-art UDA algorithms on
this new online setting using the well-known Market-1501, Duke, and MSMT17
benchmarks.
Related papers
- Generative appearance replay for continual unsupervised domain
adaptation [4.623578780480946]
GarDA is a generative-replay based approach that can adapt a segmentation model sequentially to new domains with unlabeled data.
We evaluate GarDA on two datasets with different organs and modalities, where it substantially outperforms existing techniques.
arXiv Detail & Related papers (2023-01-03T17:04:05Z) - Towards Online Domain Adaptive Object Detection [79.89082006155135]
Existing object detection models assume both the training and test data are sampled from the same source domain.
We propose a novel unified adaptation framework that adapts and improves generalization on the target domain in online settings.
arXiv Detail & Related papers (2022-04-11T17:47:22Z) - Generalizable Person Re-Identification via Self-Supervised Batch Norm
Test-Time Adaption [63.7424680360004]
Batch Norm Test-time Adaption (BNTA) is a novel re-id framework that applies the self-supervised strategy to update BN parameters adaptively.
BNTA explores the domain-aware information within unlabeled target data before inference, and accordingly modulates the feature distribution normalized by BN to adapt to the target domain.
arXiv Detail & Related papers (2022-03-01T18:46:32Z) - Lifelong Unsupervised Domain Adaptive Person Re-identification with
Coordinated Anti-forgetting and Adaptation [127.6168183074427]
We propose a new task, Lifelong Unsupervised Domain Adaptive (LUDA) person ReID.
This is challenging because it requires the model to continuously adapt to unlabeled data of the target environments.
We design an effective scheme for this task, dubbed CLUDA-ReID, where the anti-forgetting is harmoniously coordinated with the adaptation.
arXiv Detail & Related papers (2021-12-13T13:19:45Z) - Stagewise Unsupervised Domain Adaptation with Adversarial Self-Training
for Road Segmentation of Remote Sensing Images [93.50240389540252]
Road segmentation from remote sensing images is a challenging task with wide ranges of application potentials.
We propose a novel stagewise domain adaptation model called RoadDA to address the domain shift (DS) issue in this field.
Experiment results on two benchmarks demonstrate that RoadDA can efficiently reduce the domain gap and outperforms state-of-the-art methods.
arXiv Detail & Related papers (2021-08-28T09:29:14Z) - Domain adaptation for person re-identification on new unlabeled data
using AlignedReID++ [0.0]
Domain adaptation is done by using pseudo-labels generated using an unsupervised learning strategy.
Our results show that domain adaptation techniques really improve the performance of the CNN when applied in the target domain.
arXiv Detail & Related papers (2021-06-29T19:58:04Z) - Unsupervised and self-adaptative techniques for cross-domain person
re-identification [82.54691433502335]
Person Re-Identification (ReID) across non-overlapping cameras is a challenging task.
Unsupervised Domain Adaptation (UDA) is a promising alternative, as it performs feature-learning adaptation from a model trained on a source to a target domain without identity-label annotation.
In this paper, we propose a novel UDA-based ReID method that takes advantage of triplets of samples created by a new offline strategy.
arXiv Detail & Related papers (2021-03-21T23:58:39Z) - Domain Generalized Person Re-Identification via Cross-Domain Episodic
Learning [31.17248105464821]
We present an episodic learning scheme which advances meta learning strategies to exploit the observed source-domain labeled data.
Our experiments on four benchmark datasets confirm the superiority of our method over the state-of-the-arts.
arXiv Detail & Related papers (2020-10-19T14:42:29Z) - Unsupervised Disentanglement GAN for Domain Adaptive Person
Re-Identification [10.667492516216887]
We introduce a novel unsupervised disentanglement generative adversarial network (UD-GAN) to address the domain adaptation issue of supervised person ReID.
Our framework jointly trains a ReID network for discriminative features extraction in a source labelled domain using identity annotation.
As a result, the ReID features better encompass the identity of a person in the unsupervised domain.
arXiv Detail & Related papers (2020-07-30T16:07:05Z) - Structured Domain Adaptation with Online Relation Regularization for
Unsupervised Person Re-ID [62.90727103061876]
Unsupervised domain adaptation (UDA) aims at adapting the model trained on a labeled source-domain dataset to an unlabeled target-domain dataset.
We propose an end-to-end structured domain adaptation framework with an online relation-consistency regularization term.
Our proposed framework is shown to achieve state-of-the-art performance on multiple UDA tasks of person re-ID.
arXiv Detail & Related papers (2020-03-14T14:45:18Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.