MixMatch Domain Adaptaion: Prize-winning solution for both tracks of VisDA 2019 challenge

Rukhovich, Danila; Galeev, Danil

doi:10.48550/arxiv.1910.03903

Cited by 5 publications

(7 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other favored semi-supervised techniques like tritraining and virtual adversarial training have been used in 1. https://cutt.ly/DfN3rFU frameworks [83], [84], respectively. Recently, [85] directly employs MixMatch [29] and obtains promising results in the VisDA-2019 challenge. Different from prior works that treat the whole target domain as an unlabeled dataset, we focus on intra-domain semi-supervised learning where the labeled dataset consists of confident target data samples and the unlabeled dataset consists of remaining samples.…”

Section: Semi-supervised Learningmentioning

confidence: 99%

Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer

Liang

Wang

et al. 2021

IEEE Trans. Pattern Anal. Mach. Intell.

183

250

View full text Add to dashboard Cite

Unsupervised domain adaptation (UDA) aims to transfer knowledge from a related but different well-labeled source domain to a new unlabeled target domain. Most existing UDA methods require access to the source data, and thus are not applicable when the data are confidential and not shareable due to privacy concerns. This paper aims to tackle a realistic setting with only a classification model available trained over, instead of accessing to, the source data. To effectively utilize the source model for adaptation, we propose a novel approach called Source HypOthesis Transfer (SHOT), which learns the feature extraction module for the target domain by fitting the target data features to the frozen source classification module (representing classification hypothesis). Specifically, SHOT exploits both information maximization and self-supervised learning for the feature extraction module learning to ensure the target features are implicitly aligned with the features of unseen source data via the same hypothesis. Furthermore, we propose a new labeling transfer strategy, which separates the target data into two splits based on the confidence of predictions (labeling information), and then employ semi-supervised learning to improve the accuracy of less-confident predictions in the target domain. We denote labeling transfer as SHOT++ if the predictions are obtained by SHOT. Extensive experiments on both digit classification and object recognition tasks show that SHOT and SHOT++ achieve results surpassing or comparable to the state-of-the-arts, demonstrating the effectiveness of our approaches for various visual domain adaptation problems. Code will be available at https://github.com/tim-learn/SHOT-plus.

show abstract

Section: Semi-supervised Learningmentioning

confidence: 99%

Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer

Liang

Wang

et al. 2021

IEEE Trans. Pattern Anal. Mach. Intell.

183

250

View full text Add to dashboard Cite

show abstract

“…Recently, semi-supervised learning approaches [22], [23] have also shown impressive achievements on UDA problem, and Rukhovich et al [53] even wins the VisDA competition by directly exploiting MixMatch [22] in 2019. Inspired by them, we construct the proxy source domain by pseudo-labeling portions of confident samples (source-similar samples), and try to solve the SFDA task in a semi-supervised style.…”

Section: A Proxy Source Domain Construction By Prototypesmentioning

confidence: 99%

ProxyMix: Proxy-based Mixup Training with Label Refinery for Source-Free Domain Adaptation

Ding¹,

Sheng²,

Ji³

et al. 2022

Preprint

View full text Add to dashboard Cite

Unsupervised domain adaptation (UDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain. Owing to privacy concerns and heavy data transmission, source-free UDA, exploiting the pre-trained source models instead of the raw source data for target learning, has been gaining popularity in recent years. Some works attempt to recover unseen source domains with generative models, however introducing additional network parameters. Other works propose to fine-tune the source model by pseudo labels, while noisy pseudo labels may misguide the decision boundary, leading to unsatisfied results. To tackle these issues, we propose an effective method named Proxy-based Mixup training with label refinery (ProxyMix). First of all, to avoid additional parameters and explore the information in the source model, ProxyMix defines the weights of the classifier as the class prototypes and then constructs a class-balanced proxy source domain by the nearest neighbors of the prototypes to bridge the unseen source domain and the target domain. To improve the reliability of pseudo labels, we further propose the frequency-weighted aggregation strategy to generate soft pseudo labels for unlabeled target data. The proposed strategy exploits the internal structure of target features, pulls target features to their semantic neighbors, and increases the weights of low-frequency classes samples during gradient updating. With the proxy domain and the reliable pseudo labels, we employ two kinds of mixup regularization, i.e., inter-and intra-domain mixup, in our framework, to align the proxy and the target domain, enforcing the consistency of predictions, thereby further mitigating the negative impacts of noisy labels. Experiments on three 2D image and one 3D point cloud object recognition benchmarks demonstrate that ProxyMix yields state-of-the-art performance for source-free UDA tasks.

show abstract

“…Also aims to reduce the data distribution mismatch, compared with UDA, semi- supervised domain adaptation (SSDA) bridges domain discrepancy via introducing partially labeled target samples. Recently, a few methods have been proposed based on deep learning [46,32,22,35] for image classification. [46] decomposes SSDA into two sub-problems: UDA and SSL, and employ co-training [3] to exchange the expertise between two classifiers, which are trained on MixUp-ed [48] data between labeled and unlabeled data of each view.…”

Section: Related Workmentioning

confidence: 99%

Semi-supervised Domain Adaptation based on Dual-level Domain Mixing for Semantic Segmentation

Chen

Jia

et al. 2021

Preprint

View full text Add to dashboard Cite

Data-driven based approaches, in spite of great success in many tasks, have poor generalization when applied to unseen image domains, and require expensive cost of annotation especially for dense pixel prediction tasks such as semantic segmentation. Recently, both unsupervised domain adaptation (UDA) from large amounts of synthetic data and semi-supervised learning (SSL) with small set of labeled data have been studied to alleviate this issue. However, there is still a large gap on performance compared to their supervised counterparts. We focus on a more practical setting of semi-supervised domain adaptation (SSDA) where both a small set of labeled target data and large amounts of labeled source data are available. To address the task of SSDA, a novel framework based on dual-level domain mixing is proposed. The proposed framework consists of three stages. First, two kinds of data mixing methods are proposed to reduce domain gap in both region-level and sample-level respectively. We can obtain two complementary domain-mixed teachers based on dual-level mixed data from holistic and partial views respectively. Then, a student model is learned by distilling knowledge from these two teachers. Finally, pseudo labels of unlabeled data are generated in a self-training manner for another few rounds of teachers training. Extensive experimental results have demonstrated the effectiveness of our proposed framework on synthetic-to-real semantic segmentation benchmarks.

show abstract

MixMatch Domain Adaptaion: Prize-winning solution for both tracks of VisDA 2019 challenge

Cited by 5 publications

References 0 publications

Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer

Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer

ProxyMix: Proxy-based Mixup Training with Label Refinery for Source-Free Domain Adaptation

Semi-supervised Domain Adaptation based on Dual-level Domain Mixing for Semantic Segmentation

Contact Info

Product

Resources

About