Related papers: SEL-CIE: Knowledge-Guided Self-Supervised Learning…

Person image generation aims to perform non-rigid deformation on source images, which generally requires unaligned data pairs for training. Recently, self-supervised methods express great prospects in this task by merging the disentangled…

The availability of large-scale datasets has helped unleash the true potential of deep convolutional neural networks (CNNs). However, for the single-image denoising problem, capturing a real dataset is an unacceptably expensive and…

The recent increase in the extensive use of digital imaging technologies has brought with it a simultaneous demand for higher-resolution images. We develop a novel edge-informed approach to single image super-resolution (SISR). The SISR…

The recently advanced unsupervised learning approaches use the siamese-like framework to compare two "views" from the same image for learning representations. Making the two views distinctive is a core to guarantee that unsupervised methods…

Electroencephalography (EEG) plays a crucial role in brain-computer interfaces (BCIs) and neurological diagnostics, but its real-world deployment faces challenges due to noise artifacts, missing data, and high annotation costs. We introduce…

Semi-supervised learning (SSL) provides a powerful framework for leveraging unlabeled data when labels are limited or expensive to obtain. SSL algorithms based on deep neural networks have recently proven successful on standard benchmark…

The process of annotating relevant data in the field of digital microscopy can be both time-consuming and especially expensive due to the required technical skills and human-expert knowledge. Consequently, large amounts of microscopic image…

Pre-training has been proven to be effective in boosting the performance of Isolated Sign Language Recognition (ISLR). Existing pre-training methods solely focus on the compact pose data, which eliminates background perturbation but…

In most studies on learning-based image super-resolution (SR), the paired training dataset is created by downscaling high-resolution (HR) images with a predetermined operation (e.g., bicubic). However, these methods fail to super-resolve…

Most digital camera pipelines use color constancy methods to reduce the influence of illumination and camera sensor on the colors of scene objects. The highest accuracy of color correction is obtained with learning-based color constancy…

Semi-supervised learning (SSL) aims to train a machine learning model using both labelled and unlabelled data. While the unlabelled data have been used in various ways to improve the prediction accuracy, the reason why unlabelled data could…

Learning based single image super-resolution (SISR) for real-world images has been an active research topic yet a challenging task, due to the lack of paired low-resolution (LR) and high-resolution (HR) training images. Most of the existing…

In many image processing tasks it occurs that pixels or blocks of pixels are missing or lost in only some channels. For example during defective transmissions of RGB images, it may happen that one or more blocks in one color channel are…

The quality of images captured by smartphones is an important specification since smartphones are becoming ubiquitous as primary capturing devices. The traditional image signal processing (ISP) pipeline in a smartphone camera consists of…

Semi-supervised learning (SSL) has been a powerful strategy to incorporate few labels in learning better representations. In this paper, we focus on a practical scenario that one aims to apply SSL when unlabeled data may contain…

Single-pixel imaging can collect images at the wavelengths outside the reach of conventional focal plane array detectors. However, the limited image quality and lengthy computational times for iterative reconstruction still impede the…

Semi-supervised learning (SSL), which aims at leveraging a few labeled images and a large number of unlabeled images for network training, is beneficial for relieving the burden of data annotation in medical image segmentation. According to…

Self-supervised learning (SSL) has emerged as a powerful paradigm for learning representations without labeled data. Most SSL approaches rely on strong, well-established, handcrafted data augmentations to generate diverse views for…

Intrinsic image decomposition, which is an essential task in computer vision, aims to infer the reflectance and shading of the scene. It is challenging since it needs to separate one image into two components. To tackle this, conventional…

Grayscale image colorization is a fascinating application of AI for information restoration. The inherently ill-posed nature of the problem makes it even more challenging since the outputs could be multi-modal. The learning-based methods…