Related papers: Pixel-Level Self-Paced Learning for Super-Resoluti…

In this paper, we described and developed a framework for Multilayer Perceptron (MLP) to work on low level image processing, where MLP will be used to perform image super-resolution. Meanwhile, MLP are trained with different types of images…

This paper focuses on network pruning for image retrieval acceleration. Prevailing image retrieval works target at the discriminative feature learning, while little attention is paid to how to accelerate the model inference, which should be…

Recently, it has been demonstrated that deep neural networks can significantly improve the performance of single image super-resolution (SISR). Numerous studies have concentrated on raising the quantitative quality of super-resolved (SR)…

Visual place recognition (VPR) using deep networks has achieved state-of-the-art performance. However, most of them require a training set with ground truth sensor poses to obtain positive and negative samples of each observation's spatial…

Deep convolutional networks have attracted great attention in image restoration and enhancement. Generally, restoration quality has been improved by building more and more convolutional block. However, these methods mostly learn a specific…

Existing fine-tuning methods use a single learning rate over all layers. In this paper, first, we discuss that trends of layer-wise weight variations by fine-tuning using a single learning rate do not match the well-known notion that…

Existing data augmentation in self-supervised learning, while diverse, fails to preserve the inherent structure of natural images. This results in distorted augmented samples with compromised semantic information, ultimately impacting…

Image superresolution involves the processing of an image sequence to generate a still image with higher resolution. Classical approaches, such as bayesian MAP methods, require iterative minimization procedures, with high computational…

In the realms of computer vision, it is evident that deep neural networks perform better in a supervised setting with a large amount of labeled data. The representations learned with supervision are not only of high quality but also helps…

Custom and natural lighting conditions can be emulated in images of the scene during post-editing. Extraordinary capabilities of the deep learning framework can be utilized for such purpose. Deep image relighting allows automatic photo…

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…

The primary aim of single-image super-resolution is to construct high-resolution (HR) images from corresponding low-resolution (LR) inputs. In previous approaches, which have generally been supervised, the training objective typically…

Recently, pioneer work finds that speech pre-trained models can solve full-stack speech processing tasks, because the model utilizes bottom layers to learn speaker-related information and top layers to encode content-related information.…

Domain adaptation helps transfer the knowledge gained from a labeled source domain to an unlabeled target domain. During the past few years, different domain adaptation techniques have been published. One common flaw of these approaches is…

Light field imaging has recently known a regain of interest due to the availability of practical light field capturing systems that offer a wide range of applications in the field of computer vision. However, capturing high-resolution light…

The License Plate Recognition (LPR) field has made impressive advances in the last decade due to novel deep learning approaches combined with the increased availability of training data. However, it still has some open issues, especially…

Hand-held light field (LF) cameras often exhibit low spatial resolution due to the inherent trade-off between spatial and angular dimensions. Existing supervised learning-based LF spatial super-resolution (SR) methods, which rely on…

Most image super-resolution (SR) methods are developed on synthetic low-resolution (LR) and high-resolution (HR) image pairs that are constructed by a predetermined operation, e.g., bicubic downsampling. As existing methods typically learn…

Diffusion prior-based methods have shown impressive results in real-world image super-resolution (SR). However, most existing methods entangle pixel-level and semantic-level SR objectives in the training process, struggling to balance…

In recent years, deep convolutional neural network-based segmentation methods have achieved state-of-the-art performance for many medical analysis tasks. However, most of these approaches rely on optimizing the U-Net structure or adding new…