Contribution: MFT further encourages the language model to learn domain-invariant representations by jointly optimizing a series of novel domain corruption loss functions. Approach: In this paper, we propose an effective learning procedure named Meta Fine-Tuning (MFT), serving as ameta-learnerto solve...
Incremental adversarial domain adaptation (IADA) [63] adapts to continually changing domains by adversarially aligning source and target features. [59] aims to continually adapt the unseen visual domain while alleviate the forget- ting on the seen domain without retaining the source train- ing data....
and iteratively learns which domains or samples are best suited for aligning to the target. The intuition behind this is to force the Curriculum Manager to constantly re-measure the transferability of latent domains over time to adversarially raise the error rate of the domain discriminator. CMSS ...
Metric learning-based methods (UML)Unbiased metric learning: On the utilization of multiple datasets and web images for softening bias Fang, Chen, Ye Xu, and Daniel N. Rockmore. Proceedings of the IEEE International Conference on Computer Vision(ICCV) 2013. ...
(2020). Adversarial target-invariant representation learning for domain generalization. arXiv preprint arXiv:1911.00804 Balaji, Y., Sankaranarayanan, S., & Chellappa, R. (2018). Metareg: Towards domain generalization using meta-regularization. In Advances in Neural Information Processing Systems (pp....
[58] incorporates the concept of relevance between the source and target domains via meta-learning. Similarly, Meta [68] leverages domain-invariant attributes through normalization statistics, while Meta-DMoE [76] strives to extract knowledge from an aggregation of multiple experts. However, these ...
Learning Invariant Representations and Risks for Semi-supervised Domain Adaptation [CVPR2021] Attract, Perturb, and Explore: Learning a Feature Alignment Network for Semi-supervised Domain Adaptation [ECCV2020] Online Meta-Learning for Multi-Source and Semi-Supervised Domain Adaptation [ECCV2020] Bidirecti...
MetaAlign: Coordinating Domain Alignment and Classification for Unsupervised Domain Adaptation [CVPR2021] [Pytorch] Self-adaptive Re-weighted Adversarial Domain Adaptation [IJCAI2020] DIRL: Domain-Invariant Reperesentation Learning Approach for Sim-to-Real Transfer [CoRL2020] [Project] Classes Matter: A ...
MetaAlign: Coordinating Domain Alignment and Classification for Unsupervised Domain Adaptation [CVPR2021] [Pytorch] Self-adaptive Re-weighted Adversarial Domain Adaptation [IJCAI2020] DIRL: Domain-Invariant Reperesentation Learning Approach for Sim-to-Real Transfer [CoRL2020] [Project] Classes Matter: A ...
MetaReg: Towards Domain Generalization using Meta-Regularization [NIPS2018] Deep Domain Generalization via Conditional Invariant Adversarial Networks [ECCV2018] Domain Generalization with Adversarial Feature Learning [CVPR2018] Journal Correlation-aware Adversarial Domain Adaptation and Generalization [Pattern Recog...