1 code implementation • 18 May 2023 • Bin Deng, Kui Jia
We hope that our investigation and the proposed simple framework can serve as a strong baseline to facilitate future studies in this field.
no code implementations • 30 Jan 2023 • Yabin Zhang, Bin Deng, Ruihuang Li, Kui Jia, Lei Zhang
By updating the model against the adversarial statistics perturbation during training, we allow the model to explore the worst-case domain and hence improve its generalization performance.
1 code implementation • 16 Aug 2022 • Bin Deng, Kui Jia
First, we show that the key assumption of support overlap of invariant features used in IB-IRM is strong for the guarantee of OOD generalization and it is still possible to achieve the optimal solution without this assumption.
no code implementations • 18 Jun 2021 • Yabin Zhang, Bin Deng, Kui Jia, Lei Zhang
Domain adaptation becomes more challenging with increasing gaps between source and target domains.
no code implementations • 1 Jun 2021 • Yabin Zhang, Haojian Zhang, Bin Deng, Shuai Li, Kui Jia, Lei Zhang
Especially, state-of-the-art SSL methods significantly outperform existing UDA methods on the challenging UDA benchmark of DomainNet, and state-of-the-art UDA methods could be further enhanced with SSL techniques.
1 code implementation • 10 Apr 2021 • Bin Deng, Yabin Zhang, Hui Tang, Changxing Ding, Kui Jia
The great promise that UB$^2$DA makes, however, brings significant learning challenges, since domain adaptation can only rely on the predictions of unlabeled target data in a partially overlapped label space, by accessing the interface of source model.
1 code implementation • ECCV 2020 • Yabin Zhang, Bin Deng, Kui Jia, Lei Zhang
To make the proposed A$^2$LP useful for UDA, we propose empirical schemes to generate such virtual instances.
2 code implementations • 20 Feb 2020 • Yabin Zhang, Bin Deng, Hui Tang, Lei Zhang, Kui Jia
By using MCSD as a measure of domain distance, we develop a new domain adaptation bound for multi-class UDA; its data-dependent, probably approximately correct bound is also developed that naturally suggests adversarial learning objectives to align conditional feature distributions across source and target domains.
1 code implementation • IEEE Transactions on Geoscience and Remote Sensing 2019 • Bin Deng, Sen Jia, Daming Shi
In the first task, when only a few labeled samples are available, we employ ideas from metric learning based on deep embedding features and make a similarity learning between pairs of samples.
Few-Shot Image Classification Hyperspectral Image Classification +3