Related papers: MFM-DA: Instance-Aware Adaptor and Hierarchical Al…

Achieving robust generalization across diverse data domains remains a significant challenge in computer vision. This challenge is important in safety-critical applications, where deep-neural-network-based systems must perform reliably under…

In many practical applications, it is often difficult and expensive to obtain enough large-scale labeled data to train deep neural networks to their full capability. Therefore, transferring the learned knowledge from a separate, labeled…

Source-free Domain Adaptation (SFDA) aims to adapt a pre-trained source model to the unlabeled target domain without accessing the well-labeled source data, which is a much more practical setting due to the data privacy, security, and…

Deep learning has become the method of choice to tackle real-world problems in different domains, partly because of its ability to learn from data and achieve impressive performance on a wide range of applications. However, its success…

From a service perspective, Multi-Source Domain Adaptation (MSDA) is a promising scenario to adapt a deployed model to a client's dataset. It can provide adaptation without a target label and support the case where a source dataset is…

Unsupervised Domain Adaptation (UDA) can tackle the challenge that convolutional neural network(CNN)-based approaches for semantic segmentation heavily rely on the pixel-level annotated data, which is labor-intensive. However, existing UDA…

Domain adaptation (DA) aims to alleviate the domain shift between source domain and target domain. Most DA methods require access to the source data, but often that is not possible (e.g. due to data privacy or intellectual property). In…

The fine-grained localization of clinicians in the operating room (OR) is a key component to design the new generation of OR support systems. Computer vision models for person pixel-based segmentation and body-keypoints detection are needed…

Medical imaging datasets often vary due to differences in acquisition protocols, patient demographics, and imaging devices. These variations in data distribution, known as domain shift, present a significant challenge in adapting imaging…

Convolutional neural networks trained on publicly available medical imaging datasets (source domain) rarely generalise to different scanners or acquisition protocols (target domain). This motivates the active field of domain adaptation.…

Deep learning-based models in medical imaging often struggle to generalize effectively to new scans due to data heterogeneity arising from differences in hardware, acquisition parameters, population, and artifacts. This limitation presents…

Domain adaptive object detection is challenging due to distinctive data distribution between source domain and target domain. In this paper, we propose a unified multi-granularity alignment based object detection framework towards…

Unsupervised domain adaptation (UDA) in 3D segmentation tasks presents a formidable challenge, primarily stemming from the sparse and unordered nature of point cloud data. Especially for LiDAR point clouds, the domain discrepancy becomes…

Source-free domain adaptation (SFDA) is a challenging task that tackles domain shifts using only a pre-trained source model and unlabeled target data. Existing SFDA methods are restricted by the fundamental limitation of source-target…

Deployment of Deep Neural Networks in medical imaging is hindered by distribution shift between training data and data processed after deployment, causing performance degradation. Post-Deployment Adaptation (PDA) addresses this by tailoring…

Unsupervised domain adaptation techniques have been successful for a wide range of problems where supervised labels are limited. The task is to classify an unlabeled `target' dataset by leveraging a labeled `source' dataset that comes from…

Extensive studies on Unsupervised Domain Adaptation (UDA) have propelled the deployment of deep learning from limited experimental datasets into real-world unconstrained domains. Most UDA approaches align features within a common embedding…

The exploitation of visible spectrum datasets has led deep networks to show remarkable success. However, real-world tasks include low-lighting conditions which arise performance bottlenecks for models trained on large-scale RGB image…

Domain shift, characterized by degraded model performance during transition from labeled source domains to unlabeled target domains, poses a persistent challenge for deploying deep learning systems. Current unsupervised domain adaptation…

Deep networks are prone to performance degradation when there is a domain shift between the source (training) data and target (test) data. Recent test-time adaptation methods update batch normalization layers of pre-trained source models…