English
Related papers

Related papers: Navigating Beyond Dropout: An Intriguing Solution …

200 papers

Most of the recent literature on image Super-Resolution (SR) can be classified into two main approaches. The first one involves learning a corruption model tailored to a specific dataset, aiming to mimic the noise and corruption in…

Image and Video Processing · Electrical Eng. & Systems 2024-05-27 Zakariya Chaouai , Mohamed Tamaazousti

A machine learning model that generalizes well should obtain low errors on unseen test examples. Thus, if we know how to optimally perturb training examples to account for test examples, we may achieve better generalization performance.…

Machine Learning · Computer Science 2022-02-15 Hae Beom Lee , Taewook Nam , Eunho Yang , Sung Ju Hwang

Deep learning techniques have been successfully applied in many areas of computer vision, including low-level image restoration problems. For image super-resolution, several models based on deep neural networks have been recently proposed…

Computer Vision and Pattern Recognition · Computer Science 2015-10-16 Zhaowen Wang , Ding Liu , Jianchao Yang , Wei Han , Thomas Huang

Nowadays, deep learning based methods have demonstrated impressive performance on ideal super-resolution (SR) datasets, but most of these methods incur dramatically performance drops when directly applied in real-world SR reconstruction…

Computer Vision and Pattern Recognition · Computer Science 2023-08-17 Minghao She , Wendong Mao , Huihong Shi , Zhongfeng Wang

Convolutional neural networks (CNNs) have achieved remarkable success in image recognition. Although the internal patterns of the input images are effectively learned by the CNNs, these patterns only constitute a small proportion of useful…

Computer Vision and Pattern Recognition · Computer Science 2021-01-01 Zhengsu Chen , Jianwei Niu , Xuefeng Liu , Shaojie Tang

Learning generic and robust feature representations with data from multiple domains for the same problem is of great value, especially for the problems that have multiple datasets but none of them are large enough to provide abundant data…

Computer Vision and Pattern Recognition · Computer Science 2016-04-27 Tong Xiao , Hongsheng Li , Wanli Ouyang , Xiaogang Wang

Blind image deblurring remains a topic of enduring interest. Learning based approaches, especially those that employ neural networks have emerged to complement traditional model based methods and in many cases achieve vastly enhanced…

Image and Video Processing · Electrical Eng. & Systems 2019-05-30 Yuelong Li , Mohammad Tofighi , Junyi Geng , Vishal Monga , Yonina C. Eldar

In Deep Learning, Stochastic Gradient Descent (SGD) is usually selected as a training method because of its efficiency; however, recently, a problem in SGD gains research interest: sharp minima in Deep Neural Networks (DNNs) have poor…

Machine Learning · Computer Science 2018-12-04 Wei Wen , Yandan Wang , Feng Yan , Cong Xu , Chunpeng Wu , Yiran Chen , Hai Li

While training on samples drawn from independent and identical distribution has been a de facto paradigm for optimizing image classification networks, humans learn new concepts in an easy-to-hard manner and on the selected examples…

Computer Vision and Pattern Recognition · Computer Science 2020-10-16 Bowen Cheng , Yunchao Wei , Jiahui Yu , Shiyu Chang , Jinjun Xiong , Wen-Mei Hwu , Thomas S. Huang , Humphrey Shi

Image super-resolution (SR) is one of the vital image processing methods that improve the resolution of an image in the field of computer vision. In the last two decades, significant progress has been made in the field of super-resolution,…

Computer Vision and Pattern Recognition · Computer Science 2022-09-07 Syed Muhammad Arsalan Bashir , Yi Wang , Mahrukh Khan , Yilong Niu

Strong gravitational lensing provides valuable insights into the mass distribution of galaxies and the nature of dark matter. However, its modeling is computationally demanding due to the large volume of strong lensing observations. In this…

Cosmology and Nongalactic Astrophysics · Physics 2026-04-29 Juan J. Ancona-Flores , A. Hernández-Almada , V. Motta

The reconstruction of a high resolution image given a low resolution observation is an ill-posed inverse problem in imaging. Deep learning methods rely on training data to learn an end-to-end mapping from a low-resolution input to a…

Image and Video Processing · Electrical Eng. & Systems 2023-07-19 Iman Marivani , Evaggelia Tsiligianni , Bruno Cornelis , Nikos Deligiannis

Large datasets often have unreliable labels-such as those obtained from Amazon's Mechanical Turk or social media platforms-and classifiers trained on mislabeled datasets often exhibit poor performance. We present a simple, effective…

Computer Vision and Pattern Recognition · Computer Science 2017-05-10 Ishan Jindal , Matthew Nokleby , Xuewen Chen

Image deblurring has advanced rapidly with deep learning, yet most methods exhibit poor generalization beyond their training datasets, with performance dropping significantly in real-world scenarios. Our analysis shows this limitation stems…

Computer Vision and Pattern Recognition · Computer Science 2026-01-13 Yuanting Gao , Shuo Cao , Xiaohui Li , Yuandong Pu , Yihao Liu , Kai Zhang

Self-supervised learning is crucial for super-resolution because ground-truth images are usually unavailable for real-world settings. Existing methods derive self-supervision from low-resolution images by creating pseudo-pairs or by…

Image and Video Processing · Electrical Eng. & Systems 2024-11-26 Yuehan Zhang , Angela Yao

Being extremely dependent on iterative estimation of the degradation prior or optimization of the model from scratch, the existing blind super-resolution (SR) methods are generally time-consuming and less effective, as the estimation of…

Computer Vision and Pattern Recognition · Computer Science 2022-01-03 Yuanfei Huang , Jie Li , Yanting Hu , Xinbo Gao , Hua Huang

Recurrent neural networks (RNNs) are important class of architectures among neural networks useful for language modeling and sequential prediction. However, optimizing RNNs is known to be harder compared to feed-forward neural networks. A…

Machine Learning · Statistics 2018-03-29 Konrad Zolna , Devansh Arpit , Dendi Suhubdy , Yoshua Bengio

Prior methodologies have disregarded the diversities among distinct degradation types during image reconstruction, employing a uniform network model to handle multiple deteriorations. Nevertheless, we discover that prevalent degradation…

Computer Vision and Pattern Recognition · Computer Science 2025-06-10 Weilei Wen , Chunle Guo , Wenqi Ren , Hongpeng Wang , Xiuli Shao

Adversarial training has been proven to be a powerful regularization method to improve the generalization of models. However, current adversarial training methods only attack the original input sample or the embedding vectors, and their…

Machine Learning · Computer Science 2021-08-31 Shiwen Ni , Jiawen Li , Hung-Yu Kao

Regularization is important for end-to-end speech models, since the models are highly flexible and easy to overfit. Data augmentation and dropout has been important for improving end-to-end models in other domains. However, they are…

Computation and Language · Computer Science 2017-12-20 Yingbo Zhou , Caiming Xiong , Richard Socher