Related papers: Adaptive Domain Learning for Cross-domain Image De…
Medical imaging systems are commonly assessed by use of objective image quality measures. Supervised deep learning methods have been investigated to implement numerical observers for task-based image quality assessment. However, labeling…
Domain-invariant representation learning is a powerful method for domain generalization. Previous approaches face challenges such as high computational demands, training instability, and limited effectiveness with high-dimensional data,…
Medical images from different healthcare centers exhibit varied data distributions, posing significant challenges for adapting lung nodule detection due to the domain shift between training and application phases. Traditional unsupervised…
We present a novel approach for unsupervised domain adaptation (UDA) for natural images. A commonly-used objective for UDA schemes is to enhance domain alignment in representation space even if there is a domain shift in the input space.…
This paper proposes a novel pixel-level distribution regularization scheme (DRSL) for self-supervised domain adaptation of semantic segmentation. In a typical setting, the classification loss forces the semantic segmentation model to…
RAW images captured by different camera sensors exhibit substantial domain shifts due to varying spectral responses, noise characteristics, and tone behaviors, complicating their direct use in downstream computer vision tasks. Prior methods…
Recent advances in autonomous driving have underscored the importance of accurate 3D object detection, with LiDAR playing a central role due to its robustness under diverse visibility conditions. However, different vehicle platforms often…
Unsupervised domain adaptation in person re-identification resorts to labeled source data to promote the model training on target domain, facing the dilemmas caused by large domain shift and large camera variations. The non-overlapping…
This paper addresses domain adaptation for the pixel-wise classification of remotely sensed data using deep neural networks (DNN) as a strategy to reduce the requirements of DNN with respect to the availability of training data. We focus on…
Domain adaptation is one of the most crucial techniques to mitigate the domain shift problem, which exists when transferring knowledge from an abundant labeled sourced domain to a target domain with few or no labels. Partial domain…
Adversarial discriminative domain adaptation (ADDA) is an efficient framework for unsupervised domain adaptation in image classification, where the source and target domains are assumed to have the same classes, but no labels are available…
Classifiers trained on given databases perform poorly when tested on data acquired in different settings. This is explained in domain adaptation through a shift among distributions of the source and target domains. Attempts to align them…
Domain adaptation typically requires to access source domain data to utilize their distribution information for domain alignment with the target data. However, in many real-world scenarios, the source data may not be accessible during the…
Raw underwater images are degraded due to wavelength dependent light attenuation and scattering, limiting their applicability in vision systems. Another factor that makes enhancing underwater images particularly challenging is the diversity…
Since human-labeled samples are free for the target set, unsupervised person re-identification (Re-ID) has attracted much attention in recent years, by additionally exploiting the source set. However, due to the differences on camera…
The well known domain shift issue causes model performance to degrade when deployed to a new target domain with different statistics to training. Domain adaptation techniques alleviate this, but need some instances from the target domain to…
Recently, cross domain transfer has been applied for unsupervised image restoration tasks. However, directly applying existing frameworks would lead to domain-shift problems in translated images due to lack of effective supervision.…
The accuracy of deep learning (e.g., convolutional neural networks) for an image classification task critically relies on the amount of labeled training data. Aiming to solve an image classification task on a new domain that lacks labeled…
Current state-of-the-art object detectors can have significant performance drop when deployed in the wild due to domain gaps with training data. Unsupervised Domain Adaptation (UDA) is a promising approach to adapt models for new…
Applying an object detector, which is neither trained nor fine-tuned on data close to the final application, often leads to a substantial performance drop. In order to overcome this problem, it is necessary to consider a shift between…