Learning to Generalize Unseen Domains via Memory-based Multi-Source
Meta-Learning for Person Re-Identification
- URL: http://arxiv.org/abs/2012.00417v3
- Date: Fri, 7 May 2021 09:21:53 GMT
- Title: Learning to Generalize Unseen Domains via Memory-based Multi-Source
Meta-Learning for Person Re-Identification
- Authors: Yuyang Zhao, Zhun Zhong, Fengxiang Yang, Zhiming Luo, Yaojin Lin,
Shaozi Li, Nicu Sebe
- Abstract summary: We propose the Memory-based Multi-Source Meta-Learning framework to train a generalizable model for unseen domains.
We also present a meta batch normalization layer (MetaBN) to diversify meta-test features.
Experiments demonstrate that our M$3$L can effectively enhance the generalization ability of the model for unseen domains.
- Score: 59.326456778057384
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Recent advances in person re-identification (ReID) obtain impressive accuracy
in the supervised and unsupervised learning settings. However, most of the
existing methods need to train a new model for a new domain by accessing data.
Due to public privacy, the new domain data are not always accessible, leading
to a limited applicability of these methods. In this paper, we study the
problem of multi-source domain generalization in ReID, which aims to learn a
model that can perform well on unseen domains with only several labeled source
domains. To address this problem, we propose the Memory-based Multi-Source
Meta-Learning (M$^3$L) framework to train a generalizable model for unseen
domains. Specifically, a meta-learning strategy is introduced to simulate the
train-test process of domain generalization for learning more generalizable
models. To overcome the unstable meta-optimization caused by the parametric
classifier, we propose a memory-based identification loss that is
non-parametric and harmonizes with meta-learning. We also present a meta batch
normalization layer (MetaBN) to diversify meta-test features, further
establishing the advantage of meta-learning. Experiments demonstrate that our
M$^3$L can effectively enhance the generalization ability of the model for
unseen domains and can outperform the state-of-the-art methods on four
large-scale ReID datasets.
Related papers
- Learning to Generalize Unseen Domains via Multi-Source Meta Learning for Text Classification [71.08024880298613]
We study the multi-source Domain Generalization of text classification.
We propose a framework to use multiple seen domains to train a model that can achieve high accuracy in an unseen domain.
arXiv Detail & Related papers (2024-09-20T07:46:21Z) - GM-DF: Generalized Multi-Scenario Deepfake Detection [49.072106087564144]
Existing face forgery detection usually follows the paradigm of training models in a single domain.
In this paper, we elaborately investigate the generalization capacity of deepfake detection models when jointly trained on multiple face forgery detection datasets.
arXiv Detail & Related papers (2024-06-28T17:42:08Z) - Semi-supervised Meta-learning with Disentanglement for
Domain-generalised Medical Image Segmentation [15.351113774542839]
Generalising models to new data from new centres (termed here domains) remains a challenge.
We propose a novel semi-supervised meta-learning framework with disentanglement.
We show that the proposed method is robust on different segmentation tasks and achieves state-of-the-art generalisation performance on two public benchmarks.
arXiv Detail & Related papers (2021-06-24T19:50:07Z) - Domain Adaptation in Dialogue Systems using Transfer and Meta-Learning [12.64591916699374]
Current generative-based dialogue systems fail to adapt to new unseen domains when only a small amount of target data is available.
We propose a method that adapts to unseen domains by combining both transfer and meta-learning.
arXiv Detail & Related papers (2021-02-22T16:16:57Z) - Multi-Domain Adversarial Feature Generalization for Person
Re-Identification [52.835955258959785]
We propose a multi-dataset feature generalization network (MMFA-AAE)
It is capable of learning a universal domain-invariant feature representation from multiple labeled datasets and generalizing it to unseen' camera systems.
It also surpasses many state-of-the-art supervised methods and unsupervised domain adaptation methods by a large margin.
arXiv Detail & Related papers (2020-11-25T08:03:15Z) - Shape-aware Meta-learning for Generalizing Prostate MRI Segmentation to
Unseen Domains [68.73614619875814]
We present a novel shape-aware meta-learning scheme to improve the model generalization in prostate MRI segmentation.
Experimental results show that our approach outperforms many state-of-the-art generalization methods consistently across all six settings of unseen domains.
arXiv Detail & Related papers (2020-07-04T07:56:02Z) - Learning Meta Face Recognition in Unseen Domains [74.69681594452125]
We propose a novel face recognition method via meta-learning named Meta Face Recognition (MFR)
MFR synthesizes the source/target domain shift with a meta-optimization objective.
We propose two benchmarks for generalized face recognition evaluation.
arXiv Detail & Related papers (2020-03-17T14:10:30Z)
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.