Related papers: Multi-Modal Style Transfer-based Prompt Tuning for…

Deploying machine learning algorithms for robot tasks in real-world applications presents a core challenge: overcoming the domain gap between the training and the deployment environment. This is particularly difficult for visuomotor…

Unsupervised domain adaption (UDA) aims to adapt models learned from a well-annotated source domain to a target domain, where only unlabeled samples are given. Current UDA approaches learn domain-invariant features by aligning source and…

Federated domain adaptation (FDA) aims to collaboratively transfer knowledge from source clients (domains) to the related but different target client, without communicating the local data of any client. Moreover, the source clients have…

The domain discrepancy existed between medical images acquired in different situations renders a major hurdle in deploying pre-trained medical image segmentation models for clinical use. Since it is less possible to distribute training data…

Domain generalization for semantic segmentation aims to mitigate the degradation in model performance caused by domain shifts. However, in many real-world scenarios, we are unable to access the model parameters and architectural details due…

Few-shot semantic segmentation (FSS) endeavors to segment unseen classes with only a few labeled samples. Current FSS methods are commonly built on the assumption that their training and application scenarios share similar domains, and…

Federated Learning (FL) offers a powerful strategy for training machine learning models across decentralized datasets while maintaining data privacy, yet domain shifts among clients can degrade performance, particularly in medical imaging…

Multi-source unsupervised domain adaptation aims to leverage labeled data from multiple source domains for training a machine learning model to generalize well on a target domain without labels. Source domain selection plays a crucial role…

Recent advances in deep learning for medical image segmentation demonstrate expert-level accuracy. However, in clinically realistic environments, such methods have marginal performance due to differences in image domains, including…

Pretrained language models (PLMs) have made remarkable progress in text generation tasks via fine-tuning. While, it is challenging to fine-tune PLMs in a data-scarce situation. Therefore, it is non-trivial to develop a general and…

In this study, we propose a novel federated learning (FL) approach that utilizes 3D style transfer for the multi-organ segmentation task. The multi-organ dataset, obtained by integrating multiple datasets, has high scalability and can…

Deep learning models often encounter challenges in making accurate inferences when there are domain shifts between the source and target data. This issue is particularly pronounced in clinical settings due to the scarcity of annotated data…

Benefiting from prompt tuning, recent years have witnessed the promising performance of pre-trained vision-language models, e.g., CLIP, on versatile downstream tasks. In this paper, we focus on a particular setting of learning adaptive…

Graphs are able to model interconnected entities in many online services, supporting a wide range of applications on the Web. This raises an important question: How can we train a graph foundational model on multiple source domains and…

Can a text-to-image diffusion model be used as a training objective for adapting a GAN generator to another domain? In this paper, we show that the classifier-free guidance can be leveraged as a critic and enable generators to distill…

Robust whole-slide image (WSI) analysis under strict data-governance remains challenging due to substantial cross-institutional stain heterogeneity. Domain generalization (DG) mitigates these shifts but typically requires centralized data,…

Domain adaptive semantic segmentation aims to generate accurate and dense predictions for an unlabeled target domain by leveraging a supervised model trained on a labeled source domain. The prevalent self-training approach involves…

Multi-source domain adaptation has been intensively studied. The distribution shift in features inherent to specific domains causes the negative transfer problem, degrading a model's generality to unseen tasks. In Federated Learning (FL),…

Structured pruning of Generative Pre-trained Transformers (GPTs) offers a promising path to efficiency but often suffers from irreversible performance degradation due to the discarding of transformer blocks. In this paper, we introduce…

Text spotting, a task involving the extraction of textual information from image or video sequences, faces challenges in cross-domain adaption, such as image-to-image and image-to-video generalization. In this paper, we introduce a new…