hellloxiaotian / Adnet
Attention-guided CNN for image denoising(Neural Networks,2020)
Stars: ✭ 135
Projects that are alternatives of or similar to Adnet
Dltk
Deep Learning Toolkit for Medical Image Analysis
Stars: ✭ 1,249 (+825.19%)
Mutual labels: deep-neural-networks, cnn
Pytorch Learners Tutorial
PyTorch tutorial for learners
Stars: ✭ 97 (-28.15%)
Mutual labels: deep-neural-networks, cnn
Cfsrcnn
Coarse-to-Fine CNN for Image Super-Resolution (IEEE Transactions on Multimedia,2020)
Stars: ✭ 84 (-37.78%)
Mutual labels: deep-neural-networks, cnn
Awesome System For Machine Learning
A curated list of research in machine learning system. I also summarize some papers if I think they are really interesting.
Stars: ✭ 1,185 (+777.78%)
Mutual labels: deep-neural-networks, deep-reinforcement-learning
Fake news detection deep learning
Fake News Detection using Deep Learning models in Tensorflow
Stars: ✭ 74 (-45.19%)
Mutual labels: deep-neural-networks, attention-mechanism
Awesome Deep Reinforcement Learning
Curated list for Deep Reinforcement Learning (DRL): software frameworks, models, datasets, gyms, baselines...
Stars: ✭ 95 (-29.63%)
Mutual labels: deep-neural-networks, deep-reinforcement-learning
Gtsrb
Convolutional Neural Network for German Traffic Sign Recognition Benchmark
Stars: ✭ 65 (-51.85%)
Mutual labels: deep-neural-networks, cnn
Intro To Deep Learning
A collection of materials to help you learn about deep learning
Stars: ✭ 103 (-23.7%)
Mutual labels: deep-neural-networks, deep-reinforcement-learning
Sarcasm Detection
Detecting Sarcasm on Twitter using both traditonal machine learning and deep learning techniques.
Stars: ✭ 73 (-45.93%)
Mutual labels: deep-neural-networks, attention-mechanism
Hyperdensenet
This repository contains the code of HyperDenseNet, a hyper-densely connected CNN to segment medical images in multi-modal image scenarios.
Stars: ✭ 124 (-8.15%)
Mutual labels: deep-neural-networks, cnn
Noreward Rl
[ICML 2017] TensorFlow code for Curiosity-driven Exploration for Deep Reinforcement Learning
Stars: ✭ 1,176 (+771.11%)
Mutual labels: deep-neural-networks, deep-reinforcement-learning
Cnn Paper2
🎨 🎨 深度学习 卷积神经网络教程 ：图像识别，目标检测，语义分割，实例分割，人脸识别，神经风格转换，GAN等🎨🎨 https://dataxujing.github.io/CNN-paper2/
Stars: ✭ 77 (-42.96%)
Mutual labels: deep-neural-networks, cnn
Pytorch Attention Guided Cyclegan
Pytorch implementation of Unsupervised Attention-guided Image-to-Image Translation.
Stars: ✭ 67 (-50.37%)
Mutual labels: deep-neural-networks, attention-mechanism
Deep Learning Drizzle
Drench yourself in Deep Learning, Reinforcement Learning, Machine Learning, Computer Vision, and NLP by learning from these exciting lectures!!
Stars: ✭ 9,717 (+7097.78%)
Mutual labels: deep-neural-networks, deep-reinforcement-learning
Sockeye
Sequence-to-sequence framework with a focus on Neural Machine Translation based on Apache MXNet
Stars: ✭ 990 (+633.33%)
Mutual labels: deep-neural-networks, attention-mechanism
Deepseqslam
The Official Deep Learning Framework for Route-based Place Recognition
Stars: ✭ 49 (-63.7%)
Mutual labels: deep-neural-networks, cnn
Top Deep Learning
Top 200 deep learning Github repositories sorted by the number of stars.
Stars: ✭ 1,365 (+911.11%)
Mutual labels: deep-neural-networks, deep-reinforcement-learning
Lenet 5
PyTorch implementation of LeNet-5 with live visualization
Stars: ✭ 122 (-9.63%)
Mutual labels: deep-neural-networks, cnn
Atention-guided CNN for image denoising（ADNet）by Chunwei Tian, Yong Xu, Zuoyong Li, Wangmeng Zuo, Lunke Fei and Hong Liu is publised by Neural Networks, 2020 (https://www.sciencedirect.com/science/article/pii/S0893608019304241) and it is implemented by Pytorch.
This paper is pushed on home page of the Nueral Networks. Also, it is reported by wechat public accounts at https://mp.weixin.qq.com/s/Debh7PZSFTBtOVxpFh9yfQ and https://wx.zsxq.com/mweb/views/topicdetail/topicdetail.html?topic_id=548112815452544&group_id=142181451122&user_id=28514284588581&from=timeline.
This paper is the first paper via deep network properties for addressing image denoising with complex background.
Absract
Deep convolutional neural networks (CNNs) have attracted considerable interest in low-level computer vision. Researches are usually devoted to improving the performance via very deep CNNs. However, as the depth increases, influences of the shallow layers on deep layers are weakened. Inspired by the fact, we propose an attention-guided denoising convolutional neural network (ADNet), mainly including a sparse block (SB), a feature enhancement block (FEB), an attention block (AB) and a reconstruction block (RB) for image denoising. Specifically, the SB makes a tradeoff between performance and efficiency by using dilated and common convolutions to remove the noise. The FEB integrates global and local features information via a long path to enhance the expressive ability of the denoising model. The AB is used to finely extract the noise information hidden in the complex background, which is very effective for complex noisy images, especially real noisy images and bind denoising. Also, the FEB is integrated with the AB to improve the efficiency and reduce the complexity for training a denoising model. Finally, a RB aims to construct the clean image through the obtained noise mapping and the given noisy image. Additionally, comprehensive experiments show that the proposed ADNet performs very well in three tasks (i.e., synthetic and real noisy images, and blind denoising) in terms of both quantitative and qualitative evaluations. The code of ADNet is accessible at https://github.com/hellloxiaotian/ADNet.
Requirements (Pytorch)
Pytorch 0.41
Python 2.7
torchvision
openCv for Python
HDF5 for Python
Commands
Training
Training datasets
The training dataset of the gray noisy images is downloaded at https://pan.baidu.com/s/1nkY-b5_mdzliL7Y7N9JQRQ or https://drive.google.com/open?id=1_miSC9_luoUHSqMG83kqrwYjNoEus6Bj (google drive)
The training dataset of the color noisy images is downloaded at https://pan.baidu.com/s/1ou2mK5JUh-K8iMu8-DMcMw (baiduyun) or https://drive.google.com/open?id=1S1_QrP-fIXeFl5hYY193lr07KyZV8X8r (google drive)
Train ADNet-S (ADNet with known noise level)
python train.py --prepropcess True --num_of_layers 17 --mode S --noiseL 25 --val_noiseL 25
Train ADNet-B (DnCNN with blind noise level)
python train.py --preprocess True --num_of_layers 17 --mode B --val_noiseL 25
Test
Gray noisy images
python test.py --num_of_layers 17 --logdir g15 --test_data Set68 --test_noiseL 15
Gray blind denoising
python test_Gb.py --num_of_layers 17 --logdir gblind --test_data Set68 --test_noiseL 25
Color noisy images
python test_c.py --num_of_layers 17 --logdir g15 --test_data Set68 --test_noiseL 15
Color blind denoising
python test_c.py --num_of_layers 17 --logdir cblind --test_data Set68 --test_noiseL 15
Network architecture
Test Results
1. ADNet for BSD68
2. ADNet for Set12
3. ADNet for CBSD68, Kodak24 and McMaster
4. ADNet for CBSD68, Kodak24 and McMaster
5. Running time of ADNet for a noisy image of different sizes.
6. Complexity of ADNet
7. 9 real noisy images
8. 9 thermodynamic images from the proposed A
9. Visual results of BSD68
10. Visual results of Set12
11. Visual results of Kodak24
12. Visual results of McMaster
If you cite this paper, please the following format:
1.Tian C, Xu Y, Li Z, et al. Attention-guided CNN for image denoising[J]. Neural Networks, 2020, 124,177-129.
2.@article{tian2020attention,
title={Attention-guided CNN for image denoising},
author={Tian, Chunwei and Xu, Yong and Li, Zuoyong and Zuo, Wangmeng and Fei, Lunke and Liu, Hong},
journal={Neural Networks},
volume={124},
pages={177--129},
year={2020},
publisher={Elsevier}
}
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].