paper-with-me

홈 › Papers

DaMSTF: Domain Adversarial Learning Enhanced Meta Self-Training for Domain Adaptation

2023-08-05 · Menglong Lu, Zhen Huang, Yunxiang Zhao, Zhiliang Tian, Yang Liu, Dongsheng Li

Self-training emerges as an important research line on domain adaptation. By taking the model's prediction as the pseudo labels of the unlabeled data, self-training bootstraps the model with pseudo instances in the target domain. However, the prediction errors of pseudo labels (label noise) challenge the performance of self-training. To address this problem, previous approaches only use reliable pseudo instances, i.e., pseudo instances with high prediction confidence, to retrain the model. Although these strategies effectively reduce the label noise, they are prone to miss the hard examples. In this paper, we propose a new self-training framework for domain adaptation, namely Domain adversarial learning enhanced Self-Training Framework (DaMSTF). Firstly, DaMSTF involves meta-learning to estimate the importance of each pseudo instance, so as to simultaneously reduce the label noise and preserve hard examples. Secondly, we design a meta constructor for constructing the meta-validation set, which guarantees the effectiveness of the meta-learning module by improving the quality of the meta-validation set. Thirdly, we find that the meta-learning module suffers from the training guidance vanishment and tends to converge to an inferior optimal. To this end, we employ domain adversarial learning as a heuristic neural network initialization method, which can help the meta-learning module converge to a better optimal. Theoretically and experimentally, we demonstrate the effectiveness of the proposed DaMSTF. On the cross-domain sentiment classification task, DaMSTF improves the performance of BERT with an average of nearly 4%.

📄 PDF Abstract BibTeX arXiv:2308.02753

Code (0)

등록된 구현이 없습니다.

Tasks

Domain AdaptationMeta-LearningSentiment AnalysisSentiment Classification

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Adam 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Residual Connection 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
WordPiece 설명 없음

Similar Papers 제목 키워드 기반

SRoUDA: Meta Self-training for Robust Unsupervised Domain Adaptation

2022-12-12 · Wanqing Zhu, Jia-Li Yin, Bo-Hao Chen, Ximeng Liu

As acquiring manual labels on data could be costly, unsupervised domain adaptation (UDA), which transfers knowledge learned from a rich-label dataset to the unlabeled target dataset, is gaining increasing popularity. Whi…

Adversarial RobustnessDomain AdaptationUnsupervised Domain Adaptation

Debiased Dual-Invariant Defense for Adversarially Robust Person Re-Identification

2025-11-13 · Yuhang Zhou, Yanxiang Zhao, Zhongyun Hua, Zhipu Liu 외 arxiv

Person re-identification (ReID) is a fundamental task in many real-world applications such as pedestrian trajectory tracking. However, advanced deep learning-based ReID models are highly susceptible to adversarial attack…

Person Re-IdentificationAdversarial DefenseMetric Learning

MetaAlign: Coordinating Domain Alignment and Classification for Unsupervised Domain Adaptation

2021-03-25 · CVPR 2021 1 · Guoqiang Wei, Cuiling Lan, Wenjun Zeng, Zhibo Chen

For unsupervised domain adaptation (UDA), to alleviate the effect of domain shift, many approaches align the source and target domains in the feature space by adversarial learning or by explicitly aligning their statisti…

ClassificationDomain AdaptationGeneral ClassificationMeta-Learning+4

Hierarchical Self-Supervised Adversarial Training for Robust Vision Models in Histopathology

2025-03-13 · Hashmat Shadab Malik, Shahina Kunhimon, Muzammal Naseer, Fahad Shahbaz Khan 외

Adversarial attacks pose significant challenges for vision models in critical fields like healthcare, where reliability is essential. Although adversarial training has been well studied in natural images, its application…

Contrastive Learning

Learning Transferable Adversarial Robust Representations via Multi-view Consistency

2022-10-19 · Minseon Kim, Hyeonjeong Ha, Dong Bok Lee, Sung Ju Hwang

Despite the success on few-shot learning problems, most meta-learned models only focus on achieving good performance on clean examples and thus easily break down when given adversarially perturbed samples. While some rec…

Adversarial AttackAdversarial RobustnessDomain AdaptationFew-Shot Learning+3