This work presents a novel approach for semi-supervised semantic segmentation. The key
element of this approach is our contrastive learning module that enforces the segmentation …

Mixup-based augmentation has been found to be effective for generalizing models during
training, especially for Vision Transformers (ViTs) since they can easily overfit. However …

Data augmentation (DA) is an effective way to enrich the richness of data and improve a
model's generalization ability. It has been widely used in many advanced vision tasks (eg …

RGBW color filter arrays (CFAs) have gained widespread attention for their superior
performance in low-light conditions. Most existing demosaicking methods are tailored for …

With the development of Deep Neural Networks (DNNs), plenty of methods based on DNNs
have been proposed for Single Image Super-Resolution (SISR). However, existing methods …

The entire Image Signal Processor (ISP) of a camera relies on several processes to
transform the data from the Color Filter Array (CFA) sensor, such as demosaicing, denoising …

Recently, content-aware methods have been utilized to reduce the bandwidth and improve
the quality of Internet video delivery. Existing methods train corresponding content-aware …

MSE or MAE loss functions work under the premise of all pixels having equal contribution
during optimization. However, natural haze degradations are non-homogeneous, resulting …

This thesis explores the frontier of visual perception in computer vision by leveraging the
capabilities of Vision Transformers (ViTs) to create a unified framework that addresses cross …

The entire Image Signal Processor (ISP) of a camera relies on several processes to
transform the data from the Color Filter Array (CFA) sensor, such as demosaicing, denoising …