Related papers: One-to-Many Network for Visually Pleasing Compress…

The state-of-the-art performance for several real-world problems is currently reached by convolutional neural networks (CNN). Such learning models exploit recent results in the field of deep learning, typically leading to highly performing,…

We propose a data-driven approach for deep convolutional neural network compression that achieves high accuracy with high throughput and low memory requirements. Current network compression methods either find a low-rank factorization of…

Generative adversarial networks has emerged as a defacto standard for image translation problems. To successfully drive such models, one has to rely on additional networks e.g., discriminators and/or perceptual networks. Training these…

As one of the fundamental techniques for image editing, image cropping discards unrelevant contents and remains the pleasing portions of the image to enhance the overall composition and achieve better visual/aesthetic perception. In this…

The coded aperture imaging technique is a useful method of X-ray imaging in observational astrophysics. However, the presence of imaging noise or so-called artifacts in a decoded image is a drawback of this method. We propose a new coded…

Blind or no-reference (NR) perceptual picture quality prediction is a difficult, unsolved problem of great consequence to the social and streaming media industries that impacts billions of viewers daily. Unfortunately, popular NR prediction…

In the era of AIGC, the fast development of visual content generation technologies, such as diffusion models, bring potential security risks to our society. Existing generated image detection methods suffer from performance drop when faced…

This paper investigates deep neural network (DNN) compression from the perspective of compactly representing and storing trained parameters. We explore the previously overlooked opportunity of cross-layer architecture-agnostic…

Most existing dehazing algorithms often use hand-crafted features or Convolutional Neural Networks (CNN)-based methods to generate clear images using pixel-level Mean Square Error (MSE) loss. The generated images generally have better…

Medical images may contain various types of artifacts with different patterns and mixtures, which depend on many factors such as scan setting, machine condition, patients' characteristics, surrounding environment, etc. However, existing…

We present multi-point optimization: an optimization technique that allows to train several models simultaneously without the need to keep the parameters of each one individually. The proposed method is used for a thorough empirical…

In this paper, orthogonal to the existing data and model studies, we instead resort our efforts to investigate the potential of loss function in a new perspective and present our belief ``Random Weights Networks can Be Acted as Loss Prior…

Rain effect in images typically is annoying for many multimedia and computer vision tasks. For removing rain effect from a single image, deep leaning techniques have been attracting considerable attentions. This paper designs a novel…

Deep convolutional neural networks perform better on images containing spatially invariant degradations, also known as synthetic degradations; however, their performance is limited on real-degraded photographs and requires multiple-stage…

Optical and hybrid convolutional neural networks (CNNs) recently have become of increasing interest to achieve low-latency, low-power image classification and computer vision tasks. However, implementing optical nonlinearity is challenging,…

Image quality degradation caused by raindrops is one of the most important but challenging problems that reduce the performance of vision systems. Most existing raindrop removal algorithms are based on a supervised learning method using…

It is well known that Convolutional Neural Networks (CNNs) have significant redundancy in their filter weights. Various methods have been proposed in the literature to compress trained CNNs. These include techniques like pruning weights,…

For lossy image compression, we develop a neural-based system which learns a nonlinear estimator for decoding from quantized representations. The system links two recurrent networks that \help" each other reconstruct same target image…

Recent advances in learning-based image compression typically come at the cost of high complexity. Designing computationally efficient architectures remains an open challenge. In this paper, we empirically investigate the impact of…

Pruning neural networks has regained interest in recent years as a means to compress state-of-the-art deep neural networks and enable their deployment on resource-constrained devices. In this paper, we propose a robust compressive learning…