Multi-target Domain Adaptation
18 papers with code • 4 benchmarks • 4 datasets
The idea of Multi-target Domain Adaptation is to adapt a model from a single labelled source domain to multiple unlabelled target domains.
Here, we propose a new approach to domain adaptation in deep architectures that can be trained on large amount of labeled data from the source domain and large amount of unlabeled data from the target domain (no labeled target-domain data is necessary).
It can be characterized as (1) a non-adversarial DA method without explicitly deploying domain alignment, enjoying faster convergence speed; (2) a versatile approach that can handle four existing scenarios: Closed-Set, Partial-Set, Multi-Source, and Multi-Target DA, outperforming the state-of-the-art methods in these scenarios, especially on one of the largest and hardest datasets to date (7. 3% on DomainNet).
(Unsupervised) Domain Adaptation (DA) seeks for classifying target instances when solely provided with source labeled and target unlabeled examples for training.
Unsupervised domain adaptation (UDA) seeks to alleviate the problem of domain shift between the distribution of unlabeled data from the target domain w. r. t.
In this paper we address multi-target domain adaptation (MTDA), where given one labeled source dataset and multiple unlabeled target datasets that differ in data distributions, the task is to learn a robust predictor for all the target domains.
Recent advances in unsupervised domain adaptation have significantly improved the recognition accuracy of CNNs by alleviating the domain shift between (labeled) source and (unlabeled) target data distributions.
Foreground-Aware Stylization and Consensus Pseudo-Labeling for Domain Adaptation of First-Person Hand Segmentation
We validated our method on domain adaptation of hand segmentation from real and simulation images.
See Eye to Eye: A Lidar-Agnostic 3D Detection Framework for Unsupervised Multi-Target Domain Adaptation
Sampling discrepancies between different manufacturers and models of lidar sensors result in inconsistent representations of objects.
Student Becomes Decathlon Master in Retinal Vessel Segmentation via Dual-teacher Multi-target Domain Adaptation
Afterwards, knowledge distillation is performed to iteratively distill different domain knowledge from teachers to a generic student.