Thinking in frequency: Face forgery detection by mining frequency-aware clues
As realistic facial manipulation technologies have achieved remarkable progress, social
concerns about potential malicious abuse of these technologies bring out an emerging …
concerns about potential malicious abuse of these technologies bring out an emerging …
On measuring and controlling the spectral bias of the deep image prior
The deep image prior showed that a randomly initialized network with a suitable architecture
can be trained to solve inverse imaging problems by simply optimizing it's parameters to …
can be trained to solve inverse imaging problems by simply optimizing it's parameters to …
Large Kernel Frequency-enhanced Network for Efficient Single Image Super-Resolution
J Chen, C Duanmu, H Long - Proceedings of the IEEE/CVF …, 2024 - openaccess.thecvf.com
In recent years there has been significant progress in efficient and lightweight image super-
resolution due in part to the design of several powerful and lightweight attention …
resolution due in part to the design of several powerful and lightweight attention …
Spatial-frequency attention for image denoising
The recently developed transformer networks have achieved impressive performance in
image denoising by exploiting the self-attention (SA) in images. However, the existing …
image denoising by exploiting the self-attention (SA) in images. However, the existing …
DCT-FANet: DCT based frequency attention network for single image super-resolution
R Xu, X Kang, C Li, H Chen, A Ming - Displays, 2022 - Elsevier
In single-image super-resolution (SISR) task, it is challenging to recover high-frequency
details from a low-resolution (LR) image due to its ill-posed problem. Most existing CNN …
details from a low-resolution (LR) image due to its ill-posed problem. Most existing CNN …
Single image super-resolution with arbitrary magnification based on high-frequency attention network
Among various developments in the field of computer vision, single image super-resolution
of images is one of the most essential tasks. However, compared to the integer magnification …
of images is one of the most essential tasks. However, compared to the integer magnification …
Frequency Shuffling and Enhancement for Open Set Recognition
L Liu, R Wang, Y Wang, L Jing, C Wang - Proceedings of the AAAI …, 2024 - ojs.aaai.org
Open-Set Recognition (OSR) aims to accurately identify known classes while effectively
rejecting unknown classes to guarantee the reliability. Most existing OSR methods focus on …
rejecting unknown classes to guarantee the reliability. Most existing OSR methods focus on …
[PDF][PDF] Dichotomous Image Segmentation with Frequency Priors.
Y Zhou, B Dong, Y Wu, W Zhu, G Chen, Y Zhang - IJCAI, 2023 - ijcai.org
Dichotomous image segmentation (DIS) has a wide range of real-world applications and
gained increasing research attention in recent years. In this paper, we propose to tackle DIS …
gained increasing research attention in recent years. In this paper, we propose to tackle DIS …
Adaptive transform domain image super-resolution via orthogonally regularized deep networks
Deep learning methods, in particular, trained convolutional neural networks (CNNs) have
recently been shown to produce compelling results for single image super-resolution (SR) …
recently been shown to produce compelling results for single image super-resolution (SR) …
Knowledge distillation circumvents nonlinearity for optical convolutional neural networks
In recent years, convolutional neural networks (CNNs) have enabled ubiquitous image
processing applications. As such, CNNs require fast forward propagation runtime to process …
processing applications. As such, CNNs require fast forward propagation runtime to process …