Related papers: MSplit LBI: Realizing Feature Selection and Dense …

As a powerful statistical image modeling technique, sparse representation has been successfully used in various image restoration applications. The success of sparse representation owes to the development of l1-norm optimization techniques,…

Few-shot learning is a challenging problem that has attracted more and more attention recently since abundant training samples are difficult to obtain in practical applications. Meta-learning has been proposed to address this issue, which…

Although deep learning models in medical imaging often achieve excellent classification performance, they can rely on shortcut learning, exploiting spurious correlations or confounding factors that are not causally related to the target…

Deep Neural Networks have shown great promise on a variety of downstream applications; but their ability to adapt and generalize to new data and tasks remains a challenge. However, the ability to perform few or zero-shot adaptation to novel…

In image classification, "debiasing" aims to train a classifier to be less susceptible to dataset bias, the strong correlation between peripheral attributes of data samples and a target class. For example, even if the frog class in the…

Few-shot learning (FSL) aims to learn a classifier that can be easily adapted to accommodate new tasks not seen during training, given only a few examples. To handle the limited-data problem in few-shot regimes, recent methods tend to…

In visual recognition tasks, few-shot learning requires the ability to learn object categories with few support examples. Its re-popularity in light of the deep learning development is mainly in image classification. This work focuses on…

FSS(Few-shot segmentation) aims to segment a target class using a small number of labeled images(support set). To extract information relevant to the target class, a dominant approach in best-performing FSS methods removes background…

Deep learning algorithms utilizing magnetic resonance (MR) images have demonstrated cutting-edge proficiency in autonomously segmenting multiple sclerosis (MS) lesions. Despite their achievements, these algorithms may struggle to extend…

The purpose of partial multi-label feature selection is to select the most representative feature subset, where the data comes from partial multi-label datasets that have label ambiguity issues. For label disambiguation, previous methods…

Contrastive loss has been increasingly used in learning representations from multiple modalities. In the limit, the nature of the contrastive loss encourages modalities to exactly match each other in the latent space. Yet it remains an open…

Few-shot segmentation aims at assigning a category label to each image pixel with few annotated samples. It is a challenging task since the dense prediction can only be achieved under the guidance of latent features defined by sparse…

Instance segmentation for low-light imagery remains largely unexplored due to the challenges imposed by such conditions, for example shot noise due to low photon count, color distortions and reduced contrast. In this paper, we propose an…

Low-light imaging on mobile devices is typically challenging due to insufficient incident light coming through the relatively small aperture, resulting in a low signal-to-noise ratio. Most of the previous works on low-light image processing…

We consider model selection and estimation for partial spline models and propose a new regularization method in the context of smoothing splines. The regularization method has a simple yet elegant form, consisting of roughness penalty on…

Among applications of deep learning (DL) involving low cost sensors, remote image classification involves a physical channel that separates edge sensors and cloud classifiers. Traditional DL models must be divided between an encoder for the…

High levels of noise usually exist in today's captured images due to the relatively small sensors equipped in the smartphone cameras, where the noise brings extra challenges to lossy image compression algorithms. Without the capacity to…

Few-shot learning (FSL), which aims to recognise new classes by adapting the learned knowledge with extremely limited few-shot (support) examples, remains an important open problem in computer vision. Most of the existing methods for…

Light field (LF) images acquired by hand-held devices usually suffer from low spatial resolution as the limited detector resolution has to be shared with the angular dimension. LF spatial super-resolution (SR) thus becomes an indispensable…

In recent years, learned image compression (LIC) methods have achieved significant performance improvements. However, obtaining a more compact latent representation and reducing the impact of quantization errors remain key challenges in the…