Related papers: Adaptive Mix for Semi-Supervised Medical Image Seg…

In many machine learning applications, it is important for the model to provide confidence scores that accurately capture its prediction uncertainty. Although modern learning methods have achieved great success in predictive accuracy,…

Advanced data augmentation strategies have widely been studied to improve the generalization ability of deep learning models. Regional dropout is one of the popular solutions that guides the model to focus on less discriminative parts by…

Data augmentation has become a standard component of vision pre-trained models to capture the invariance between augmented views. In practice, augmentation techniques that mask regions of a sample with zero/mean values or patches from other…

Contrastive self-supervised learning has attracted significant research attention recently. It learns effective visual representations from unlabeled data by embedding augmented views of the same image close to each other while pushing away…

MixUp is an effective data augmentation method to regularize deep neural networks via random linear interpolations between pairs of samples and their labels. It plays an important role in model regularization, semi-supervised learning and…

The performance of supervised deep learning methods for medical image segmentation is often limited by the scarcity of labeled data. As a promising research direction, semi-supervised learning addresses this dilemma by leveraging unlabeled…

In medical imaging, the heterogeneity of multi-centre data impedes the applicability of deep learning-based methods and results in significant performance degradation when applying models in an unseen data domain, e.g. a new centreor a new…

Given the special situation of modeling gigapixel images, multiple instance learning (MIL) has become one of the most important frameworks for Whole Slide Image (WSI) classification. In current practice, most MIL networks often face two…

Self-supervised Multi-modal Contrastive Learning (SMCL) remarkably advances modern Vision-Language Pre-training (VLP) models by aligning visual and linguistic modalities. Due to noises in web-harvested text-image pairs, however, scaling up…

Deep learning has shown remarkable progress in medical image semantic segmentation, yet its success heavily depends on large-scale expert annotations and consistent data distributions. In practice, annotations are scarce, and images are…

Deep learning approaches to the segmentation of magnetic resonance images have shown significant promise in automating the quantitative analysis of brain images. However, a continuing challenge has been its sensitivity to the variability of…

Modern data augmentation using a mixture-based technique can regularize the models from overfitting to the training data in various computer vision applications, but a proper data augmentation technique tailored for the part-based…

A key challenge in machine learning is to generalize from training data to an application domain of interest. This work generalizes the recently-proposed mixture invariant training (MixIT) algorithm to perform unsupervised learning in the…

In weakly supervised medical image segmentation, the absence of structural priors and the discreteness of class feature distribution present a challenge, i.e., how to accurately propagate supervision signals from local to global regions…

Due to the imbalanced and limited data, semi-supervised medical image segmentation methods often fail to produce superior performance for some specific tailed classes. Inadequate training for those particular classes could introduce more…

Scribble-supervised medical image segmentation tackles the limitation of sparse masks. Conventional approaches alternate between: labeling pseudo-masks and optimizing network parameters. However, such iterative two-stage paradigm is…

Studies on semi-supervised medical image segmentation (SSMIS) have seen fast progress recently. Due to the limited labelled data, SSMIS methods mainly focus on effectively leveraging unlabeled data to enhance the segmentation performance.…

MixUp is a computer vision data augmentation technique that uses convex interpolations of input data and their labels to enhance model generalization during training. However, the application of MixUp to the natural language understanding…

Deep-learning based speech separation models confront poor generalization problem that even the state-of-the-art models could abruptly fail when evaluating them in mismatch conditions. To address this problem, we propose an…

Semi-supervised learning addresses the issue of limited annotations in medical images effectively, but its performance is often inadequate for complex backgrounds and challenging tasks. Multi-modal fusion methods can significantly improve…