Channel Attention and Multi-level Features Fusion for Single Image Super-Resolution

Lu, Yue; Zhou, Yun; Jiang, Zhuqing; Guo, Xiaoqiang; Yang, Zixuan

doi:10.1109/vcip.2018.8698663

Cited by 29 publications

(14 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…SCA-CNN [29] incorporates both spatial and channel-wise attention in a CNN to facilitate the task of image caption. [30] proposes a compact channel attention combined with the multi-level feature fusion mechanism which benefits image super-resolution.…”

Section: Self-attentionmentioning

confidence: 99%

All You Need Is a Second Look: Towards Arbitrary-Shaped Text Detection

Cao

Zhang

Yang

et al. 2022

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

Arbitrary-shaped text detection is a challenging task since curved texts in the wild are of the complex geometric layouts. Existing mainstream methods follow the instance segmentation pipeline to obtain the text regions. However, arbitraryshaped texts are difficult to be depicted through one single segmentation network because of the varying scales. In this paper, we propose a two-stage segmentation-based detector, termed as NASK (Need A Second looK), for arbitrary-shaped text detection. Compared to the traditional single-stage segmentation network, our NASK conducts the detection in a coarse-to-fine manner with the first stage segmentation spotting the rectangle text proposals and the second one retrieving compact representations. Specifically, NASK is composed of a Text Instance Segmentation (TIS) network (1 stage), a Geometry-aware Text RoI Alignment (GeoAlign) module, and a Fiducial pOint eXpression (FOX) module (2 stage). Firstly, TIS extracts the augmented features with a novel Group Spatial and Channel Attention (GSCA) module and conducts instance segmentation to obtain rectangle proposals. Then, GeoAlign converts these rectangles into the fixed size and encodes RoI-wise feature representation. Finally, FOX disintegrates the text instance into serval pivotal geometrical attributes to refine the detection results. Extensive experimental results on three public benchmarks including Total-Text, SCUT-CTW1500, and ICDAR 2015 verify that our NASK outperforms recent state-of-the-art methods.

show abstract

Section: Self-attentionmentioning

confidence: 99%

All You Need Is a Second Look: Towards Arbitrary-Shaped Text Detection

Cao

Zhang

Yang

et al. 2022

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

show abstract

“…Attention mechanism can be used in super-resolution tasks to focus on the high-frequency details of the image, suppress the image noise and improve the performance of the reconstructed image. (Lu et al 2018) used channel attention to calibrate input elements, and aggregated multi-level features and shared recursive unit parameters to improve reconstruction quality. (Liu et al 2018) used attention method to distinguish texture region and smooth region to restore high-frequency details effectively.…”

Section: Attention Mechanismmentioning

confidence: 99%

Image Super Resolution Reconstruction Based on Improved Invertible Rescaling Net

Chen

2021

Preprint

View full text Add to dashboard Cite

The Invertible Rescaling Net (IRN) is modeling image downscaling and upscaling as a unified task to alleviate the ill-posed problem in the super-resolution task. However, the ability of potential variables of the model embedded high-frequency information is general, which affects the performance of the reconstructed image. In order to improve the ability of embedding high-frequency information and further reduce the complexity of the model, the potential variables and feature extraction of key components of IRN are improved. Attention mechanism and dilated convolution are used to improve the feature extraction block, reduce the parameters of feature extraction block, and allocate more attention to the image details. The high frequency sub-band interpolation method of wavelet domain is used to improve the potential variables, process and save the image edge, and enhance the ability of embedding high frequency information. Experimental results show that compared with IRN model, improved model has less complexity and excellent performance.

show abstract

“…Channel attention [12] provides an effective technique to recalibrate channel-wise features adaptively by explicitly modeling interdependencies between channels. Previous studies have proven the effectiveness of channel attention block [25,5,43,16] in the task of super-resolution. In the proposed OAM, we adopt the channel attention mechanism described in [16] to adaptively combine orientation-aware features to generate more distinctive features as:…”

Section: Orientation-aware Feature Extraction and Channel Attention Modulementioning

confidence: 99%

Orientation-Aware Deep Neural Network for Real Image Super-Resolution

Sun

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

View full text Add to dashboard Cite

Recently, Convolutional Neural Network (CNN) based approaches have achieved impressive single image superresolution (SISR) performance in terms of accuracy and visual effects. It is noted that most SISR methods assume that the low-resolution (LR) images are obtained through bicubic interpolation down-sampling, thus their performance on real-world LR images is limited. In this paper, we proposed a novel orientation-aware deep neural network (OA-DNN) model, which incorporate a number of orientation feature extraction and channel attention modules (OAMs), to achieve good SR performance on real-world LR images captured by a single-lens reflex (DSLR) camera. Orientation-aware features extracted in different directions are adaptively combined through a channel-wise attention mechanism to generate more distinctive features for high-fidelity recovery of image details. Moreover, we reshape the input image into smaller spatial size but deeper depth via an inverse pixel-shuffle operation to accelerate the training/testing speed without sacrificing restoration accuracy. Extensive experimental results indicate that our OA-DNN model achieves a good balance between accuracy and speed. The extended OA-DNN * + model further increases PSNR index by 0.18 dB compared with our previously submitted version. Codes will be made public after publication.

show abstract

Channel Attention and Multi-level Features Fusion for Single Image Super-Resolution

Cited by 29 publications

References 18 publications

All You Need Is a Second Look: Towards Arbitrary-Shaped Text Detection

All You Need Is a Second Look: Towards Arbitrary-Shaped Text Detection

Image Super Resolution Reconstruction Based on Improved Invertible Rescaling Net

Orientation-Aware Deep Neural Network for Real Image Super-Resolution

Contact Info

Product

Resources

About