Related papers: Controlled Data Rebalancing in Multi-Task Learning…

Over the past decade a wide spectrum of machine learning models have been developed to model the neurodegenerative diseases, associating biomarkers, especially non-intrusive neuroimaging markers, with key clinical scores measuring the…

Learning from imbalanced data is one of the most significant challenges in real-world classification tasks. In such cases, neural networks performance is substantially impaired due to preference towards the majority class. Existing…

Training Single-Image Super-Resolution (SISR) models using pixel-based regression losses can achieve high distortion metrics scores (e.g., PSNR and SSIM), but often results in blurry images due to insufficient recovery of high-frequency…

Different from traditional image super-resolution task, real image super-resolution(Real-SR) focus on the relationship between real-world high-resolution(HR) and low-resolution(LR) image. Most of the traditional image SR obtains the LR…

Task-oriented image semantic communication is a new communication paradigm, which aims to transmit semantics for artificial intelligent (AI) tasks while ignoring the reconstruction quality of the images. However, in some applications, such…

In this work, we investigate the understudied effect of the training data used for image super-resolution (SR). Most commonly, novel SR methods are developed and benchmarked on common training datasets such as DIV2K and DF2K. However, we…

Training a single model on multiple input domains and/or output tasks allows for compressing information from multiple sources into a unified backbone hence improves model efficiency. It also enables potential positive knowledge transfer…

Using single-task deep learning methods to reconstruct Magnetic Resonance Imaging (MRI) data acquired with different imaging sequences is inherently challenging. The trained deep learning model typically lacks generalizability, and the…

Spatially varying image deblurring remains a fundamentally ill-posed problem, especially when degradations arise from complex mixtures of motion and other forms of blur under significant noise. State-of-the-art learning-based approaches…

Image super-resolution (SR) is a field in computer vision that focuses on reconstructing high-resolution images from the respective low-resolution image. However, super-resolution is a well-known ill-posed problem as most methods rely on…

Deep learning models suffer from catastrophic forgetting when learning new tasks incrementally. Incremental learning has been proposed to retain the knowledge of old classes while learning to identify new classes. A typical approach is to…

How to extract more and useful information for single image super resolution is an imperative and difficult problem. Learning-based method is a representative method for such task. However, the results are not so stable as there may exist…

Recognising detailed facial or clothing attributes in images of people is a challenging task for computer vision, especially when the training data are both in very large scale and extremely imbalanced among different attribute classes. To…

While tasks could come with varying the number of instances and classes in realistic settings, the existing meta-learning approaches for few-shot classification assume that the number of instances per task and class is fixed. Due to such…

Realistic image super-resolution (SR) focuses on transforming real-world low-resolution (LR) images into high-resolution (HR) ones, handling more complex degradation patterns than synthetic SR tasks. This is critical for applications like…

In real-world scenarios, image recognition tasks, such as semantic segmentation and object detection, often pose greater challenges due to the lack of information available within low-resolution (LR) content. Image super-resolution (SR) is…

Recent advances in self-supervised learning, predominantly studied in high-level visual tasks, have been explored in low-level image processing. This paper introduces a novel self-supervised constraint for single image super-resolution,…

Regression tasks in computer vision, such as age estimation or counting, are often formulated into classification by quantizing the target space into classes. Yet real-world data is often imbalanced -- the majority of training samples lie…

The training of real-world super-resolution reconstruction models heavily relies on datasets that reflect real-world degradation patterns. Extracting and modeling degradation patterns for super-resolution reconstruction using only…

Super-resolution (SR) techniques designed for real-world applications commonly encounter two primary challenges: generalization performance and restoration accuracy. We demonstrate that when methods are trained using complex, large-range…