Self-ensembling for visual domain adaptation

By Geoffrey French, Michal Mackiewicz, Mark H. Fisher. 2017

559 citations recorded by the source corpus.

Subfields: Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Representation & Self-Supervised Learning

Citations in the corpus

FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence (2020, methodology): “Similar justiﬁca-tions have been used in the past for ignoring low-conﬁdence predictions in visual domain adaptation [14].”
Incremental Object Detection via Meta-Learning (2020, neutral): “This has found success in semi-supervised learning [50], [51], [52] and domain adaptation [53], [54], [55], [56] settings.”
Moment Matching for Multi-Source Domain Adaptation (2018, methodology): “For example, SE [7] performs the best when there is a limit number of categories, but worst when the number of categories is larger than 150.”
There Are Many Consistent Explanations of Unlabeled Data: Why You Should Average (2018, methodology): “A recent model by French et al. (2018) applies the consistency enforcing principle for domain adaptation and achieves state-of-the-art results on many datasets.”
Neural Snowball for Few-Shot Relation Learning (2019, background): “Many other semi-supervised methods can also be adopted for RE (Blum and Mitchell, 1998; Rosenberg et al., 2005; French et al., 2017; Lin et al., 2019), yet they still require sufﬁcient labeled data and mainly aim at classifying predeﬁned relations rather than discovering new relations.”
Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision (2023, background): “…pseudo-labels is widely used in semi-supervised learning (Laine & Aila, 2016; Tarvainen & Valpola, 2017; Xie et al., 2020), domain adaptation (French et al., 2017; Shu et al., 2018), and knowledge distillation (Hinton et al., 2015; Gou et al., 2021; Stanton et al., 2021; Beyer et al., 2022).”
Maximum Density Divergence for Domain Adaptation (2020, unknown): “1 ∗Self-Ensembling [39] 98.”
Domain Adaptation for Semantic Segmentation With Maximum Squares Loss (2019, background): “These semi-supervised learning based approaches achieve state-of-the-art results in both classiﬁcation [9] and semantic segmentation [36].”
MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation (2022, methodology): “To increase the robustness of the self-training, consistency regularization [63, 67, 71] is often applied to ensure consistency over different data augmentations [1, 9, 18, 54], different crops [31, 38], multiple models [88, 93, 94], or domain-mixup [30–32, 72, 95].”
Improving Consistency-Based Semi-Supervised Learning with Weight Averaging (2018, methodology): “Method VADA [26] SE [5] SE + SWA Test Error 20.”
Self-Ensembling With GAN-Based Data Augmentation for Domain Adaptation in Semantic Segmentation (2019, methodology): “We adopt selfensembling [9], one of the effective methods for domain adaptation in classification.”
Unsupervised domain adaptation for medical imaging segmentation with self-ensembling (2018, methodology): “The Mean Teacher framework was also extended for unsupervised domain adaptation in (French et al., 2017).”
Self-Ensembling Attention Networks: Addressing Domain Shift for Semantic Segmentation (2019, background): “French et al. extend this model to deal with the unsupervised domain adaptation (French, Mackiewicz, and Fisher 2018), but this work does not propose any segmentation speciﬁc adaptation approach.”
A Noise-Robust Framework for Automatic Segmentation of COVID-19 Pneumonia Lesions From CT Images (2020, methodology): “Differently from previous self-ensembling methods for semi-supervised learning [20], [21] and domain adaptation [22], [23], we propose two adaptive mechanisms to better deal with noisy labels: adaptive teacher that suppresses the contribution of the student to EMA when the latter has a large…”
Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectives (2022, background): “Following AdaBN, several works have shown that the BN alignment can be added on top of other UDA methods (Li, 2018; Bousmalis et al., 2018; French et al., 2017; Kang et al., 2019).”
Milking CowMask for Semi-Supervised Image Classification (2020, methodology): “In place of a ramp-up we opt to use confidence thresholding (French et al., 2018).”
AdaGraph: Unifying Predictive and Continuous Domain Adaptation Through Graphs (2019, background): “. Related Works Unsupervised Deep Domain Adaptation. Previous works on deep DA learn deep domain invariant representations by exploiting different architectures, such as Convolutional Neural Networks [18,27,8,3,17,7,1], deep autoencoders [32] or GANs [26,13]. Some methods describe source and target ”
Cluster Alignment With a Teacher for Unsupervised Domain Adaptation (2019, methodology): “Recent attempts to apply SSL techniques in UDA include [6, 41, 46].”