Related papers: Transfer Learning by Asymmetric Image Weighting fo…

Conformal prediction constructs a set of labels instead of a single point prediction, while providing a probabilistic coverage guarantee. Beyond the coverage guarantee, adaptiveness to example difficulty is an important property. It means…

Transfer learning assumes classifiers of similar tasks share certain parameter structures. Unfortunately, modern classifiers uses sophisticated feature representations with huge parameter spaces which lead to costly transfer. Under the…

We study the problem of aligning the supports of distributions. Compared to the existing work on distribution alignment, support alignment does not require the densities to be matched. We propose symmetric support difference as a divergence…

In general, objects can be distinguished on the basis of their features, such as color or shape. In particular, it is assumed that similarity judgments about such features can be processed independently in different metric spaces. However,…

Learning similarity is a key aspect in medical image analysis, particularly in recommendation systems or in uncovering the interpretation of anatomical data in images. Most existing methods learn such similarities in the embedding space…

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…

Distance metric learning (DML) approaches learn a transformation to a representation space where distance is in correspondence with a predefined notion of similarity. While such models offer a number of compelling benefits, it has been…

Image segmentation enables to extract quantitative measures from scans that can serve as imaging biomarkers for diseases. However, segmentation quality can vary substantially across scans, and therefore yield unfaithful estimates in the…

Scarcity of high quality annotated images remains a limiting factor for training accurate image segmentation models. While more and more annotated datasets become publicly available, the number of samples in each individual database is…

Deep learning has become a promising approach for automated medical diagnoses. When medical data samples are limited, collaboration among multiple institutions is necessary to achieve high algorithm performance. However, sharing patient…

Image classification, which classifies images by pre-defined categories, has been the dominant approach to visual representation learning over the last decade. Visual learning through image-text alignment, however, has emerged to show…

Deep learning methodologies have been employed in several different fields, with an outstanding success in image recognition applications, such as material quality control, medical imaging, autonomous driving, etc. Deep learning models rely…

Automatically discovering image categories in unlabeled natural images is one of the important goals of unsupervised learning. However, the task is challenging and even human beings define visual categories based on a large amount of prior…

We propose a semantic similarity metric for image registration. Existing metrics like euclidean distance or normalized cross-correlation focus on aligning intensity values, giving difficulties with low intensity contrast or noise. Our…

Learning to transfer visual attributes requires supervision dataset. Corresponding images with varying attribute values with the same identity are required for learning the transfer function. This largely limits their applications, because…

Self-supervised learning is a powerful paradigm for representation learning on unlabelled images. A wealth of effective new methods based on instance matching rely on data-augmentation to drive learning, and these have reached a rough…

Deep learning has demonstrated significant improvements in medical image segmentation using a sufficiently large amount of training data with manual labels. Acquiring well-representative labels requires expert knowledge and exhaustive…

The development of highly accurate deep learning methods for indoor localization is often hindered by the unavailability of sufficient data measurements in the desired environment to perform model training. To overcome the challenge of…

Can models generalize attribute knowledge across semantically and perceptually dissimilar categories? While prior work has addressed attribute prediction within narrow taxonomic or visually similar domains, it remains unclear whether…

The performance of deep segmentation models often degrades due to distribution shifts in image intensities between the training and test data sets. This is particularly pronounced in multi-centre studies involving data acquired using…