(2020). Adversarial target-invariant representation learning for domain generalization. arXiv preprint arXiv:1911.00804 Balaji, Y., Sankaranarayanan, S., & Chellappa, R. (2018). Metareg: Towards domain generali
as it can effectively address class space disparities among source domains. RaMoE [58] incorporates the concept of relevance between the source and target domains via meta-learning. Similarly
Adversarial Invariant Feature Learning with Accuracy Constraint for Domain Generalization [ECMLPKDD 2019] [Code] (AFLAC) [84] Feature Alignment and Restoration for Domain Generalization and Adaptation [arXiv 2020] (FAR) [189] Representation via Representations: Domain Generalization via Adversarially Learne...
To learn generalisable representations, gradient-based meta-learning can be applied as a leaning strategy when giving multi-domain data (Liu et al., 2021b). Shin et al. (2021) disentangle intensity and non-intensity for domain adaptation in CT images. Kalkhof et al. (2022) also disentangle...
Nonlinear invariant risk minimiza- tion: A causal approach. arXiv:2102.12353, 2021. 1, 2 [52] David Madras, Elliot Creager, Toniann Pitassi, and Richard Zemel. Learning adversarially fair and transferable represen- tations. In ICML, 2018. 3 [53] Lars Mescheder, Andreas...
Semantics disentangling for generalized zero-shot learning. In IEEE/CVF International Conference on Computer Vision (ICCV), 2021. [6] Xinjie Fan, Qifei Wang, Junjie Ke, Feng Yang, Boqing Gong, and Mingyuan Zhou. Adversarially adaptive normal- ization for single domain ...
Approach: In this paper, we propose an effective learning procedure named Meta Fine-Tuning (MFT), serving as a meta-learner to solve a group of similar NLP tasks for neural language models. It further encourages the language model to encode domain-invariant representations by optimizing a series...
(ASR-Norm)Adversarially Adaptive Normalization for Single Domain GeneralizationFan, Xinjie, Qifei Wang, Junjie Ke, Feng Yang, Boqing Gong, and Mingyuan Zhou.Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition(CVPR) 2021. ...
but also transfers domain-invariant information to the model as prior knowledge. This promotes the model in better distinguishing between domain-private and domain-shared features, which is crucial for learning shared features that are beneficial for the task at hand. Mining shared features from multi...
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....