Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identification

Zhao, Yuyang; Zhong, Zhun; Yang, Fengxiang; Luo, Zhiming; Lin, Yaojin; Li, Shaozi; Sebe, Nicu

doi:10.1109/cvpr46437.2021.00621

Cited by 158 publications

(76 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some recent works [25], [26], [27] evaluated heterogeneous DG on an instance retrieval task, i.e. cross-dataset person re-ID [72], [73], which better fits the heterogeneous DG requirements. 2…”

Section: Problem Definitionmentioning

confidence: 99%

“…training and evaluation are performed under the same set of camera views, with performance almost reaching saturation. Recently, cross-dataset re-ID [39], [72], [73] has gained significant interests. The objective is to generalize a re-ID model learned from source camera views to target camera views installed in a different environment.…”

Section: Action Recognitionmentioning

confidence: 99%

“…The existing DG works [25], [26], [27] have investigated cross-dataset re-ID between Market1501 [142] and DukeMTMC-reID [122], [123]. A few works [72], [73] have attempted the multiple-to-one setting, e.g., using Mar-ket1501, CUHK03 [145] and MSMT17 [146] for training and DukeMTMC-reID for testing.…”

Section: Action Recognitionmentioning

confidence: 99%

“…[22], [23], [31], [34], [72], [73], [95], [96], [164], [165], [166] Data Augmentation ( § 3.3) -Hand-Engineered Transformations [32], [33], [65], [86], [167], [168], [169], [170] -Gradient-Based Augmentation [24], [40], [45], [171] -Model-Based Augmentation [19], [25], [26], [137], [172], [173], [174], [175], [176] -Feature-Based Augmentation [27], [86], [177], [178] Ensemble Learning ( § 3.4) -Exemplar-SVMs [47], [50], [179] -Domain-Specific Neural Networks [104], [138], [180], [181], [182] -Domain-Specific Batch Normalization [183], [184], [185], [186] -Weight Averaging [187] Network Architecture Design ( § 3.5) -Exploiting Instance Normalization [39], [57], [58], [59], [188] -Problem-Specific Modules ...…”

Section: Action Recognitionmentioning

confidence: 99%

“…Meta-learning has been a fast growing area with applications to many machine learning and computer vision problems [22], [34], [72], [96], [209]. Also known as learningto-learning, meta-learning aims to learn from episodes sampled from related tasks to benefit future learning (see [210] for a comprehensive survey on meta-learning).…”

Section: Meta-learningmentioning

confidence: 99%

See 4 more Smart Citations

Domain Generalization: A Survey

Zhou¹,

Liu²,

Qiao³

et al. 2021

Preprint

View full text Add to dashboard Cite

Generalization to out-of-distribution (OOD) data is a capability natural to humans yet challenging for machines to reproduce. This is because most statistical learning algorithms strongly rely on the i.i.d. assumption on source/target data, while in practice domain shift between source and target is common. Domain generalization (DG) aims to achieve OOD generalization by using only source data for model learning. Since first introduced in 2011, research in DG has made great progresses. In particular, intensive research in this topic has led to a broad spectrum of methodologies, e.g., those based on domain alignment, meta-learning, data augmentation, or ensemble learning, just to name a few; and has covered various applications such as object recognition, segmentation, action recognition, and person re-identification. In this paper, for the first time, a comprehensive literature review is provided to summarize the developments in DG in the past decade. Specifically, we first cover the background by formally defining DG and relating it to other research fields like domain adaptation and transfer learning. Second, we conduct a thorough review into existing methods and present a categorization based on their methodologies and motivations. Finally, we conclude this survey with insights and discussions on future research directions.

show abstract

Section: Problem Definitionmentioning

confidence: 99%

Section: Action Recognitionmentioning

confidence: 99%

Section: Action Recognitionmentioning

confidence: 99%

Section: Action Recognitionmentioning

confidence: 99%

Section: Meta-learningmentioning

confidence: 99%

See 3 more Smart Citations

Domain Generalization: A Survey

Zhou¹,

Liu²,

Qiao³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

Adaptive wavelet‐VNet for single‐sample test time adaptation in medical image segmentation

Qian,

Lu,

Zhang

2024

Medical Physics

View full text Add to dashboard Cite

BackgroundIn medical image segmentation, a domain gap often exists between training and testing datasets due to different scanners or imaging protocols, which leads to performance degradation in deep learning‐based segmentation models. Given the high cost of manual labeling and the need for privacy protection, it is often challenging to annotate the testing (target) domain data for model fine‐tuning or to collect data from different domains to train domain generalization models. Therefore, using only unlabeled target domain data for test‐time adaptation (TTA) presents a more practical but challenging solution.PurposeTo improve the segmentation accuracy of deep learning‐based models on unseen datasets, and especially to enhance the efficiency and stability of TTA for individual samples from heterogeneous domains.MethodsIn this study, we proposed to dynamically adapt a wavelet‐VNet (WaVNet) to unseen target domains with a hybrid objective function, based on each unlabeled test sample during the test time. We embedded multiscale wavelet coefficients into a V‐Net encoder and adaptively adjusted the spatial and spectral features according to the input, and the model parameters were optimized by three loss functions. We integrated a shape‐aware loss to focus on the foreground segmentations, a Refine loss to correct the incomplete and noisy segmentations caused by domain shifts, and an entropy loss to promote the global consistency of the segmentations. We evaluated the proposed method on multidomain liver and prostate segmentation datasets to assess its advantages over other TTA methods. For the source domain model training of the liver dataset, we used 15 3D MR image samples for training and 5 for validation. Correspondingly, for the prostate dataset, we used 22 3D MR image samples for training and 7 for validation. In the target domain, we used a single 3D MR image sample for adaptation and testing. The total number of testing samples is 60 in the liver dataset (for 3 different domains) and 116 in the prostate dataset (for 6 different domains).ResultsThe proposed method showed the highest segmentation accuracy among all methods, achieving a mean (± SD) Dice coefficient (DSC) of 78.10 ± 5.23% and a mean 95th Hausdorff distance (HD95) of 15.52 ± 5.84 mm on the liver dataset; and a mean DSC of 80.02 ± 3.89% and a mean HD95 of 9.18 ± 3.47 mm on the prostate dataset. The DSC is 11.67% (in absolute terms) and 15.27% higher than that of the baseline (no adaptation) method, for the liver and the prostate datasets, respectively.ConclusionsThe proposed adaptive WaVNet enhanced the image segmentation accuracy from unseen domains during the test time via unsupervised learning and multi‐objective optimization. It can benefit clinical applications where data are scarce or with changing data distributions, including online adaptive radiotherapy. The code will be released at: https://github.com/sanny1226/WaVNet.

show abstract

Spatial Foreground Bigraph Matching for Generalizable Person Re-identification

Zhang¹,

Yang²

2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identification

Cited by 158 publications

References 32 publications

Domain Generalization: A Survey

Domain Generalization: A Survey

Adaptive wavelet‐VNet for single‐sample test time adaptation in medical image segmentation

Spatial Foreground Bigraph Matching for Generalizable Person Re-identification

Contact Info

Product

Resources

About