Cross-Scale Residual Network: A General Framework for Image Super-Resolution, Denoising, and Deblocking

Zhou, Yuan; Du, Xiaoting; Wang, Mingfei; Huo, Shuwei; Zhang, Yeda; Kung, Sun‐Yuan

doi:10.1109/tcyb.2020.3044374

Cited by 23 publications

(3 citation statements)

References 68 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Li et al [38] introduced dynamic convolution to the multi-source domain adaptation task to address domain shift. Zhou et al [39] proposed a cross-scale residual network, which can extract multiple spatial scale features and establish multiple temporal feature reusage. Compared with the above methods, our DSA module utilises the dynamic selection mechanism and residual network to overcome scale variation and the complex representation capability of dynamic convolution to overcome the domain shift problem.…”

Section: Dynamic Convolutionmentioning

confidence: 99%

Domain adaptive crowd counting via dynamic scale aggregation network

Huo

Wang

Qiao

et al. 2023

IET Computer Vision

View full text Add to dashboard Cite

Crowd counting is an important research topic in computer vision. Its goal is to estimate the people's number in an image. Researchers have dramatically improved counting accuracy in recent years by regressing density maps. However, because of the inherent domain shift, the model trained on an expensive manually labelled dataset (source domain) does not perform well on a dataset with scarce labels (target domain). For this issue, a novel dynamic scale aggregation network (DSANet) is proposed to reduce the gaps in style and cross‐domain head scale variations. Specifically, a practical style transfer layer is introduced to reduce the appearance discrepancy between the source and target domains. Then, the translated source and target domain samples are encoded by a generator consisting of the VGG16 network and the dynamic scale aggregation modules (DSA Modules) and produce corresponding density maps. The DSA module can adaptively adjust parameters according to the input features and effectively fuse multi‐scale information to overcome the cross‐domain head scale variations. Next, a discriminator judges the input density map from the source or target domain. Last, domain distributions are aligned through adversarial between the generator and the discriminator. The experiments show that our network outperforms the current state‐of‐the‐art methods and can improve the target domain's performance while maintaining the source domain's performance without significant degradation.

show abstract

Section: Dynamic Convolutionmentioning

confidence: 99%

Domain adaptive crowd counting via dynamic scale aggregation network

Huo

Wang

Qiao

et al. 2023

IET Computer Vision

View full text Add to dashboard Cite

show abstract

“…In the context of 5G and IoT, this study addresses technical limitations associated with low-quality videos: specifically, poor lighting and low spatial resolution. These difficulties have an impact on the perceptual quality of video streams [13][14][15] and introduce factors such as poor lighting, camera noise, low spatial resolution, and low frame rates [9,[16][17][18][19]. Despite these challenges, various techniques for detecting anomalies in low-quality surveillance videos have been proposed, [20,21].…”

Section: Introductionmentioning

confidence: 99%

Edge-Enhanced TempoFuseNet: A Two-Stream Framework for Intelligent Multiclass Video Anomaly Recognition in 5G and IoT Environments

Saleem,

Bajwa,

Raza

et al. 2024

Future Internet

View full text Add to dashboard Cite

Surveillance video analytics encounters unprecedented challenges in 5G and IoT environments, including complex intra-class variations, short-term and long-term temporal dynamics, and variable video quality. This study introduces Edge-Enhanced TempoFuseNet, a cutting-edge framework that strategically reduces spatial resolution to allow the processing of low-resolution images. A dual upscaling methodology based on bicubic interpolation and an encoder–bank–decoder configuration is used for anomaly classification. The two-stream architecture combines the power of a pre-trained Convolutional Neural Network (CNN) for spatial feature extraction from RGB imagery in the spatial stream, while the temporal stream focuses on learning short-term temporal characteristics, reducing the computational burden of optical flow. To analyze long-term temporal patterns, the extracted features from both streams are combined and routed through a Gated Recurrent Unit (GRU) layer. The proposed framework (TempoFuseNet) outperforms the encoder–bank–decoder model in terms of performance metrics, achieving a multiclass macro average accuracy of 92.28%, an F1-score of 69.29%, and a false positive rate of 4.41%. This study presents a significant advancement in the field of video anomaly recognition and provides a comprehensive solution to the complex challenges posed by real-world surveillance scenarios in the context of 5G and IoT.

show abstract

“…Recently, due to plug-in network architectures and flexible training mechanisms, deep networks have strong self-learning ability to gain better restoration performance [24,39,76]. For instance, Cui et al used multiple stacked auto-encoders with non-local self-similarity in image super-resolution [7].…”

Section: Introductionmentioning

confidence: 99%

Image Super-resolution with An Enhanced Group Convolutional Neural Network

Tian¹,

Yuan²,

Zhang³

et al. 2022

Preprint

View full text Add to dashboard Cite

CNNs with strong learning abilities are widely chosen to resolve super-resolution problem. However, CNNs depend on deeper network architectures to improve performance of image superresolution, which may increase computational cost in general. In this paper, we present an enhanced super-resolution group CNN (ESRGCNN) with a shallow architecture by fully fusing deep and wide channel features to extract more accurate low-frequency information in terms of correlations of different channels in single image super-resolution (SISR). Also, a signal enhancement operation in the ESRGCNN is useful to inherit more long-distance contextual information for resolving long-term dependency. An adaptive up-sampling operation is gathered into a CNN to obtain an image super-resolution model with low-resolution images of different sizes. Extensive experiments report that our ESRGCNN surpasses the state-of-the-arts in terms of SISR performance, complexity, execution speed, image quality evaluation and visual effect in SISR. Code is found at https://github.com/hellloxiaotian/ESRGCNN.

show abstract

Cross-Scale Residual Network: A General Framework for Image Super-Resolution, Denoising, and Deblocking

Cited by 23 publications

References 68 publications

Domain adaptive crowd counting via dynamic scale aggregation network

Domain adaptive crowd counting via dynamic scale aggregation network

Edge-Enhanced TempoFuseNet: A Two-Stream Framework for Intelligent Multiclass Video Anomaly Recognition in 5G and IoT Environments

Image Super-resolution with An Enhanced Group Convolutional Neural Network

Contact Info

Product

Resources

About