The generalization capability of models during inference in medical imaging, especially across data from different centers, is crucial, particularly in the context of limited data availability. Semi-supervised domain generalization learning has explored the use of unlabeled data to help the model generalize to unseen domains. However, existing methods primarily focus on decoupling and fusing information within the source distribution, resulting in limited improvement to the generalization ability. In contrast, we extend the exploration beyond source distributions and propose domain distribution boundary perturbation consistency learning for semi-supervised domain generalization in segmentation. We first use normalizing flows to map features to a mixture of Gaussian distributions, enabling the model to capture complex and diverse feature distributions across domains. Then, we perturb the features towards the domain boundaries and apply consistency regularization to maintain the quality of pseudo-labels while encouraging exploration of out-of-distribution features. This exploration aids the model's adaptation to unseen domains and enhances generalization. Our method is simple and effective, outperforming existing state-of-the-art approaches on three public benchmark datasets and achieving optimal generalization performance.

Color fundus photography (CFP) and optical coherence tomography (OCT) are two common modalities used in eye disease screening, providing crucial complementary information for the diagnosis of eye diseases. However, existing multimodal learning methods cannot fully leverage the information from each modality due to the large dimensional and semantic gap between 2D CFP and 3D OCT images, leading to suboptimal classification performance. To bridge the modality gap and fully exploit the information from each modality, we propose a novel feature disentanglement method that decomposes features into modality-shared and modality-specific components. We design a multi-level regularization strategy including intra-modality, intermodality, and intra-inter-modality regularization to facilitate the effective learning of the modality Shared-Specific features. Our method achieves state-of-the-art performance on two eye disease diagnosis tasks using two publicly available datasets. Our method promises to serve as a useful tool for multimodal eye disease diagnosis. The source code is publicly available at https://github.com/yuerjiar/ShaSpec

3D point cloud registration is a fundamental problem in computer vision and robotics. Recently, learning-based point cloud registration methods have made great progress. However, these methods are sensitive to outliers, which lead to more incorrect correspondences. In this paper, we propose a novel deep graph matching-based framework for point cloud registration. Specifically, we first transform point clouds into graphs and extract deep features for each point. Then, we develop a module based on deep graph matching to calculate a soft correspondence matrix. By using graph matching, not only the local geometry of each point but also its structure and topology in a larger range are considered in establishing correspondences, so that more correct correspondences are found. We train the network with a loss directly defined on the correspondences, and in the test stage the soft correspondences are transformed into hard one-to-one correspondences so that registration can be performed by a correspondence-based solver. Furthermore, we introduce a transformer-based method to generate edges for graph construction, which further improves the quality of the correspondences. Extensive experiments on object-level and scene-level benchmark datasets show that the proposed method achieves state-of-the-art performance.