Related papers: Label Super Resolution with Inter-Instance Loss

The advancement of deep learning has greatly improved supervised image classification. However, labeling data is costly, prompting research into unsupervised learning methods such as contrastive learning. In real-world scenarios, fully…

High-resolution images for remote sensing applications are often not affordable or accessible, especially when in need of a wide temporal span of recordings. Given the easy access to low-resolution (LR) images from satellites, many remote…

This paper presents a simple yet effective two-stage framework for semi-supervised medical image segmentation. Unlike prior state-of-the-art semi-supervised segmentation methods that predominantly rely on pseudo supervision directly on…

Rich and accurate medical image segmentation is poised to underpin the next generation of AI-defined clinical practice by delineating critical anatomy for pre-operative planning, guiding real-time intra-operative navigation, and supporting…

Semi-supervised learning (SSL) can reduce the need for large labelled datasets by incorporating unlabelled data into the training. This is particularly interesting for semantic segmentation, where labelling data is very costly and…

Despite the superior performance of Deep Learning (DL) on numerous segmentation tasks, the DL-based approaches are notoriously overconfident about their prediction with highly polarized label probability. This is often not desirable for…

Deep neural networks have reached remarkable achievements in medical image processing tasks, specifically in classifying and detecting various diseases. However, when confronted with limited data, these networks face a critical…

Implicit neural representations (INRs) have emerged as a powerful tool for solving inverse problems in computer vision and computational imaging. INRs represent images as continuous domain functions realized by a neural network taking…

Image retrieval has become an increasingly appealing technique with broad multimedia application prospects, where deep hashing serves as the dominant branch towards low storage and efficient retrieval. In this paper, we carried out in-depth…

Image super-resolution (SR) is a technique to recover lost high-frequency information in low-resolution (LR) images. Spatial-domain information has been widely exploited to implement image SR, so a new trend is to involve frequency-domain…

Learning with Label Proportions (LLP) is the problem of recovering the underlying true labels given a dataset when the data is presented in the form of bags. This paradigm is particularly suitable in contexts where providing individual…

Implicit neural representations (INRs) have achieved remarkable successes in learning expressive yet compact signal representations. However, they are not naturally amenable to predictive tasks such as segmentation, where they must learn…

Real-world image super-resolution (Real-ISR) has achieved a remarkable leap by leveraging large-scale text-to-image models, enabling realistic image restoration from given recognition textual prompts. However, these methods sometimes fail…

Rare diseases are characterized by low prevalence and are often chronically debilitating or life-threatening. Imaging-based classification of rare diseases is challenging due to the severe shortage in training examples. Few-shot learning…

Recent years have seen significant developments in the field of License Plate Recognition (LPR) through the integration of deep learning techniques and the increasing availability of training data. Nevertheless, reconstructing license…

Weakly supervised segmentation methods can delineate thyroid nodules in ultrasound images efficiently using training data with coarse labels, but suffer from: 1) low-confidence pseudo-labels that follow topological priors, introducing…

Accurately segmenting a variety of clinically significant lesions from whole body computed tomography (CT) scans is a critical task on precision oncology imaging, denoted as universal lesion segmentation (ULS). Manual annotation is the…

Hyperspectral imaging (HSI) holds significant potential for transforming the field of computational pathology. However, there is currently a shortage of pixel-wise annotated HSI data necessary for training deep learning (DL) models.…

Satellite imagery is a cornerstone for numerous Remote Sensing (RS) applications; however, limited spatial resolution frequently hinders the precision of such systems, especially in multi-label scene classification tasks as it requires a…

High-performance deep learning methods typically rely on large annotated training datasets, which are difficult to obtain in many clinical applications due to the high cost of medical image labeling. Existing data assessment methods…