相关论文: Domain Generalization by Learning from Privileged …

Humans have the ability to accumulate knowledge of new tasks in varying conditions, but deep neural networks often suffer from catastrophic forgetting of previously learned knowledge after learning a new task. Many recent methods focus on…

The success of deep learning has set new benchmarks for many medical image analysis tasks. However, deep models often fail to generalize in the presence of distribution shifts between training (source) data and test (target) data. One…

Deploying deep learning models in clinical practice often requires leveraging multiple data modalities, such as images, text, and structured data, to achieve robust and trustworthy decisions. However, not all modalities are always available…

This paper presents a new approach of transfer learning-based medical image classification to mitigate insufficient labeled data problem in medical domain. Instead of direct transfer learning from source to small number of labeled target…

Although deep learning models like CNNs have achieved great success in medical image analysis, the small size of medical datasets remains a major bottleneck in this area. To address this problem, researchers have started looking for…

Learning the similarity between images constitutes the foundation for numerous vision tasks. The common paradigm is discriminative metric learning, which seeks an embedding that separates different training classes. However, the main…

Multi-modality is widely used in medical imaging, because it can provide multiinformation about a target (tumor, organ or tissue). Segmentation using multimodality consists of fusing multi-information to improve the segmentation. Recently,…

Digitization techniques for biomedical images yield different visual patterns in radiological exams. These differences may hamper the use of data-driven approaches for inference over these images, such as Deep Neural Networks. Another…

The recent prevalence of deep neural networks has lead semantic segmentation networks to achieve human-level performance in the medical field when sufficient training data is provided. Such networks however fail to generalize when tasked…

Practical learning-based autonomous driving models must be capable of generalizing learned behaviors from simulated to real domains, and from training data to unseen domains with unusual image properties. In this paper, we investigate…

Domain generalization aims at training machine learning models to perform robustly across different and unseen domains. Several recent methods use multiple datasets to train models to extract domain-invariant features, hoping to generalize…

Recent studies have proven that DNNs, unlike human vision, tend to exploit texture information rather than shape. Such texture bias is one of the factors for the poor generalization performance of DNNs. We observe that the texture bias…

Despite the recent success of domain generalization in medical image segmentation, voxel-wise annotation for all source domains remains a huge burden. Semi-supervised domain generalization has been proposed very recently to combat this…

Unsupervised approaches for learning representations invariant to common transformations are used quite often for object recognition. Learning invariances makes models more robust and practical to use in real-world scenarios. Since data…

Deep learning has been widely used for medical image segmentation and a large number of papers has been presented recording the success of deep learning in the field. In this paper, we present a comprehensive thematic survey on medical…

Retinal vessel segmentation plays a key role in computer-aided screening, diagnosis, and treatment of various cardiovascular and ophthalmic diseases. Recently, deep learning-based retinal vessel segmentation algorithms have achieved…

Domain generalization refers to the problem where we aim to train a model on data from a set of source domains so that the model can generalize to unseen target domains. Naively training a model on the aggregate set of data (pooled from all…

When the training and test data are from different distributions, domain adaptation is needed to reduce dataset bias to improve the model's generalization ability. Since it is difficult to directly match the cross-domain joint…

The accuracy and robustness of image classification with supervised deep learning are dependent on the availability of large-scale, annotated training data. However, there is a paucity of annotated data available due to the complexity of…

Hard parameter sharing in multi-domain learning (MDL) allows domains to share some of the model parameters to reduce storage cost while improving prediction accuracy. One common sharing practice is to share the bottom layers of a deep…