2023-03-13 更新
Generative Model Based Noise Robust Training for Unsupervised Domain Adaptation
Authors:Zhongying Deng, Da Li, Junjun He, Yi-Zhe Song, Tao Xiang
Target domain pseudo-labelling has shown effectiveness in unsupervised domain adaptation (UDA). However, pseudo-labels of unlabeled target domain data are inevitably noisy due to the distribution shift between source and target domains. This paper proposes a Generative model-based Noise-Robust Training method (GeNRT), which eliminates domain shift while mitigating label noise. GeNRT incorporates a Distribution-based Class-wise Feature Augmentation (D-CFA) and a Generative-Discriminative classifier Consistency (GDC), both based on the class-wise target distributions modelled by generative models. D-CFA minimizes the domain gap by augmenting the source data with distribution-sampled target features, and trains a noise-robust discriminative classifier by using target domain knowledge from the generative models. GDC regards all the class-wise generative models as generative classifiers and enforces a consistency regularization between the generative and discriminative classifiers. It exploits an ensemble of target knowledge from all the generative models to train a noise-robust discriminative classifier and eventually gets theoretically linked to the Ben-David domain adaptation theorem for reducing the domain gap. Extensive experiments on Office-Home, PACS, and Digit-Five show that our GeNRT achieves comparable performance to state-of-the-art methods under single-source and multi-source UDA settings.
PDF
点此查看论文截图
Knowledge Transfer via Multi-Head Feature Adaptation for Whole Slide Image Classification
Authors:Conghao Xiong, Yi Lin, Hao Chen, Joseph Sung, Irwin King
Transferring prior knowledge from a source domain to the same or similar target domain can greatly enhance the performance of models on the target domain. However, it is challenging to directly leverage the knowledge from the source domain due to task discrepancy and domain shift. To bridge the gaps between different tasks and domains, we propose a Multi-Head Feature Adaptation module, which projects features in the source feature space to a new space that is more similar to the target space. Knowledge transfer is particularly important in Whole Slide Image (WSI) classification since the number of WSIs in one dataset might be too small to achieve satisfactory performance. Therefore, WSI classification is an ideal testbed for our method, and we adapt multiple knowledge transfer methods for WSI classification. The experimental results show that models with knowledge transfer outperform models that are trained from scratch by a large margin regardless of the number of WSIs in the datasets, and our method achieves state-of-the-art performances among other knowledge transfer methods on multiple datasets, including TCGA-RCC, TCGA-NSCLC, and Camelyon16 datasets.
PDF
点此查看论文截图
Sliced-Wasserstein on Symmetric Positive Definite Matrices for M/EEG Signals
Authors:Clément Bonet, Benoît Malézieux, Alain Rakotomamonjy, Lucas Drumetz, Thomas Moreau, Matthieu Kowalski, Nicolas Courty
When dealing with electro or magnetoencephalography records, many supervised prediction tasks are solved by working with covariance matrices to summarize the signals. Learning with these matrices requires using Riemanian geometry to account for their structure. In this paper, we propose a new method to deal with distributions of covariance matrices and demonstrate its computational efficiency on M/EEG multivariate time series. More specifically, we define a Sliced-Wasserstein distance between measures of symmetric positive definite matrices that comes with strong theoretical guarantees. Then, we take advantage of its properties and kernel methods to apply this distance to brain-age prediction from MEG data and compare it to state-of-the-art algorithms based on Riemannian geometry. Finally, we show that it is an efficient surrogate to the Wasserstein distance in domain adaptation for Brain Computer Interface applications.
PDF
点此查看论文截图
Bi3D: Bi-domain Active Learning for Cross-domain 3D Object Detection
Authors:Jiakang Yuan, Bo Zhang, Xiangchao Yan, Tao Chen, Botian Shi, Yikang Li, Yu Qiao
Unsupervised Domain Adaptation (UDA) technique has been explored in 3D cross-domain tasks recently. Though preliminary progress has been made, the performance gap between the UDA-based 3D model and the supervised one trained with fully annotated target domain is still large. This motivates us to consider selecting partial-yet-important target data and labeling them at a minimum cost, to achieve a good trade-off between high performance and low annotation cost. To this end, we propose a Bi-domain active learning approach, namely Bi3D, to solve the cross-domain 3D object detection task. The Bi3D first develops a domainness-aware source sampling strategy, which identifies target-domain-like samples from the source domain to avoid the model being interfered by irrelevant source data. Then a diversity-based target sampling strategy is developed, which selects the most informative subset of target domain to improve the model adaptability to the target domain using as little annotation budget as possible. Experiments are conducted on typical cross-domain adaptation scenarios including cross-LiDAR-beam, cross-country, and cross-sensor, where Bi3D achieves a promising target-domain detection accuracy (89.63% on KITTI) compared with UDAbased work (84.29%), even surpassing the detector trained on the full set of the labeled target domain (88.98%). Our code is available at: https://github.com/PJLabADG/3DTrans.
PDF Accepted by CVPR2023; Code is available at https://github.com/PJLabADG/3DTrans
点此查看论文截图
Boosting Open-Set Domain Adaptation with Threshold Self-Tuning and Cross-Domain Mixup
Authors:Xinghong Liu, Yi Zhou, Tao Zhou, Jie Qin, Shengcai Liao
Open-set domain adaptation (OSDA) aims to not only recognize target samples belonging to common classes shared by source and target domains but also perceive unknown class samples. Existing OSDA methods suffer from two obstacles. First, a tedious process of manually tuning a hyperparameter $threshold$ is required for most OSDA approaches to separate common and unknown classes. It is difficult to determine a proper threshold when the target domain data is unlabeled. Second, most OSDA methods only rely on confidence values predicted by models to distinguish common/unknown classes. The performance is not satisfied, especially when the majority of the target domain consists of unknown classes. Our experiments demonstrate that combining entropy, consistency, and confidence is a more reliable way of distinguishing common and unknown samples. In this paper, we design a novel threshold self-tuning and cross-domain mixup (TSCM) method to overcome the two drawbacks. TSCM can automatically tune a proper threshold utilizing unlabeled target samples rather than manually setting an empirical hyperparameter. Our method considers multiple criteria instead of only the confidence and uses the threshold generated by itself to separate common and unknown classes in the target domain. Furthermore, we introduce a cross-domain mixup method designed for OSDA scenarios to learn domain-invariant features in a more continuous latent space. Comprehensive experiments illustrate that our method consistently achieves superior performance on different benchmarks compared with various state-of-the-arts.
PDF
点此查看论文截图