Multiple Expert Brainstorming for Domain Adaptive Person Re-identification

@article{Zhai2020MultipleEB,
  title={Multiple Expert Brainstorming for Domain Adaptive Person Re-identification},
  author={Yunpeng Zhai and Qixiang Ye and Shijian Lu and Mengxi Jia and Rongrong Ji and Yonghong Tian},
  journal={ArXiv},
  year={2020},
  volume={abs/2007.01546}
}
Often the best performing deep neural models are ensembles of multiple base-level networks, nevertheless, ensemble learning with respect to domain adaptive person re-ID remains unexplored. In this paper, we propose a multiple expert brainstorming network (MEB-Net) for domain adaptive person re-ID, opening up a promising direction about model ensemble problem under unsupervised conditions. MEB-Net adopts a mutual learning strategy, where multiple networks with different architectures are pre… 

Figures, Tables, and Topics from this paper

Multiple Domain Experts Collaborative Learning: Multi-Source Domain Generalization For Person Re-Identification
TLDR
Extensive experiments on DG-ReID benchmarks show that the MD-ExCo outperforms the state-of-the-art methods by a large margin, showing its ability to improve the generalization capability of the ReID models.
Unsupervised Domain Adaptive Person Re-Identification via Human Learning Imitation
TLDR
A new method to imitate the human learning process from different aspects, i.e., adaptively updating learning materials, selectively imitating teacher behaviors, and analyzing learning materials structures is proposed, which is called Human Learning Imitation framework.
Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identification
TLDR
The Memory-based Multi-Source Meta-Learning (M3L) framework to train a generalizable model for unseen domains is proposed and a meta-learning strategy is introduced to simulate the train-test process of domain generalization for learning more generalizable models.
Unsupervised Cross Domain Person Re-Identification by Multi-Loss Optimization Learning
TLDR
A multi-loss optimization learning (MLOL) model is proposed for UCD person re-ID in order to alleviate the erroneous guidance brought by the clustering error to the model, a ranking-average-based triplet loss learning and a neighbor-consistency-based loss learning are developed.
Lifelong Unsupervised Domain Adaptive Person Re-identification with Coordinated Anti-forgetting and Adaptation
TLDR
An effective scheme for this task, dubbed CLUDA-ReID, where the anti-forgetting is harmoniously coordinated with the adaptation, and a meta-based Coordinated Data Replay strategy is proposed to replay old data and update the network with a coordinated optimization direction for both adaptation and memorization.
Rethinking Sampling Strategies for Unsupervised Person Re-identification
  • Xumeng Han, Xuehui Yu, +5 authors Zhenjun Han
  • Computer Science
  • 2021
TLDR
This paper suggests that deteriorated over-fitting is an important factor causing poor performance, and enhancing statistical stability can rectify this issue, and proposes a simple yet effective approach, known as group sampling, which gathers groups of samples from the same class into a mini-batch.
Towards Discriminative Representation Learning for Unsupervised Person Re-identification
TLDR
This work proposes a cluster-wise contrastive learning algorithm (CCL) by iterative optimization of feature learning and cluster refinery to learn noise-tolerant representations in the unsupervised manner and adopts a progressive domain adaptation (PDA) strategy to gradually mitigate the domain gap between source and target data.
Stable Median Centre Clustering for Unsupervised Domain Adaptation Person Re-Identification
TLDR
A stable median centre clustering (SMCC) for the unsupervised domain adaptation person re-ID method is proposed, which adaptively mines credible samples for optimization purposes and reduces the impact of label noise and outliers on training to improve the performance of the resulting model.
Multi-Centroid Representation Network for Domain Adaptive Person Re-ID
TLDR
This paper presents a novel Multi-Centroid Memory (MCM) to adaptively capture different identity information within the cluster and proposes Second-Order Nearest Interpolation (SONI) to obtain abundant and informative negative samples.
Exploiting Sample Uncertainty for Domain Adaptive Person Re-Identification
TLDR
This paper proposes to estimate and exploit the credibility of the assigned pseudo-label of each sample to alleviate the influence of noisy labels, by suppressing the contribution of noisy samples, and introduces uncertainty-guided optimization that brings significant improvement and achieves the state-of-the-art performance on benchmark datasets.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 55 REFERENCES
Part-aware Progressive Unsupervised Domain Adaptation for Person Re-Identification
  • Fan Yang, Ke Yan, +6 authors W. Gao
  • Computer Science
    IEEE Transactions on Multimedia
  • 2021
TLDR
An innovative part-aware progressive adaptation network (PPAN) that exploits global and local relations for UDA-based ReID across domains and a novel progressive adaptation strategy (PAS) is designed that effectively alleviates the negative influence of outlier source identities.
Adaptive Transfer Network for Cross-Domain Person Re-Identification
TLDR
A novel adaptive transfer network (ATNet) for effective cross-domain person re-identification that decomposes the complicated cross- domain transfer into a set of factor-wise sub-transfers and gives ATNet the capability of precise style transfer at factor level and eventually effective transfer across domains.
Self-Similarity Grouping: A Simple Unsupervised Cross Domain Adaptation Approach for Person Re-Identification
TLDR
A Self-similarity Grouping (SSG) approach, which exploits the potential similarity of unlabeled samples to build multiple clusters from different views automatically, and introduces a clustering-guided semisupervised approach named SSG ++ to conduct the one-shot domain adaption in an open set setting.
Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-Identification
TLDR
Results on three re-ID domains show that the domain adaptation accuracy outperforms the state of the art by a large margin and the three invariance properties and the proposed memory are indispensable towards an effective domain adaptation system.
Self-Training With Progressive Augmentation for Unsupervised Cross-Domain Person Re-Identification
TLDR
A self-training method with progressive augmentation framework (PAST) to promote the model performance progressively on the target dataset and introduces a ranking-based triplet loss in the conservative stage, which is a label-free objective function based on the similarities between data pairs.
Unsupervised Domain Adaptive Re-Identification: Theory and Practice
TLDR
A novel self-training scheme for unsupervised domain adaptive re-identification (re-ID) that iteratively makes guesses for unlabeled target data based on an encoder and trains the encoder based on the guessed labels.
AD-Cluster: Augmented Discriminative Clustering for Domain Adaptive Person Re-Identification
TLDR
A novel augmented discriminative clustering (AD-Cluster) technique that estimates and augments person clusters in target domains and enforces the discrimination ability of re-ID models with the augmented clusters.
Unsupervised Person Re-identification
TLDR
A progressive unsupervised learning (PUL) method to transfer pretrained deep representations to unseen domains and demonstrates that PUL outputs discriminative features that improve the re-ID accuracy.
Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification
TLDR
A novel soft softmax-triplet loss is proposed to support learning with soft pseudo triplet labels for achieving the optimal domain adaptation performance in person re-identification models.
Clustering and Dynamic Sampling Based Unsupervised Domain Adaptation for Person Re-Identification
TLDR
A Clustering and Dynamic Sampling (CDS) method is proposed in this paper, which tries to transfer the useful knowledge of existing labeled source domain to the unlabeled target one to improve the discriminability of CNN model on source domain.
...
1
2
3
4
5
...