Large-scale labeled training datasets have enabled deep neural networks to excel across a wide range of benchmark vision tasks. However, in many applications, it is prohibitively …
Machine learning systems generally assume that the training and testing distributions are the same. To this end, a key requirement is to develop models that can generalize to unseen …
Currently, cross-scene hyperspectral image (HSI) classification has drawn increasing attention. It is necessary to train a model only on source domain (SD) and directly …
P Wang, Z Zhang, Z Lei… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
The goal of domain generalization (DG) is to enhance the generalization capability of the model learned from a source domain to other unseen domains. The recently developed …
J Liang, D Hu, J Feng - International conference on machine …, 2020 - proceedings.mlr.press
Unsupervised domain adaptation (UDA) aims to leverage the knowledge learned from a labeled source dataset to solve similar tasks in a new unlabeled domain. Prior UDA …
There are a variety of Domain Adaptation (DA) scenarios subject to label sets and domain configurations, including closed-set and partial-set DA, as well as multi-source and multi …
Unsupervised domain adaptation (DA) has gained substantial interest in semantic segmentation. However, almost all prior arts assume concurrent access to both labeled …
We introduce D omain-specific M asks for G eneralization, a model for improving both in- domain and out-of-domain generalization performance. For domain generalization, the goal …
X Peng, Z Huang, Y Zhu, K Saenko - arXiv preprint arXiv:1911.02054, 2019 - arxiv.org
Federated learning improves data privacy and efficiency in machine learning performed over networks of distributed devices, such as mobile phones, IoT and wearable devices, etc …