Multistage supervised contrastive learning for hybrid-degraded image restoration

Fu, Bo; Dong, Yuhan; Fu, Shilin; Wu, Yuechu; Ren, Yonggong; Thanh, Dang N. H.

doi:10.1007/s11760-022-02262-8

Cited by 10 publications

(5 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The aim of image DM is recovering a RGB image from a mosaic image losing two-thirds information. Various traditional methods [15]- [23] and deep learning methods [24] have been presented. Besides, due to noise commonly existing in the real world, DM methods usually need collaboration of DN methods [25], [26], and process the noisy mosaic image sequentially.…”

Section: Joint Denoising and Demosaicingmentioning

confidence: 99%

Deep Guided Attention Network for Joint Denoising and Demosaicing in Real Image

Zhang,

Fu,

Zhang

2024

Chinese J. Elect.

View full text Add to dashboard Cite

Denoising (DN) and demosaicing (DM) are the first crucial stages in the image signal processing pipeline. Recently, researches pay more attention to solve DN and DM in a joint manner, which is an extremely undetermined inverse problem. Existing deep learning methods learn the desired prior on synthetic dataset, which limits the generalization of learned network to the real world data. Moreover, existing methods mainly focus on the raw data property of high green information sampling rate for DM, but occasionally exploit the high intensity and signalto-noise (SNR) of green channel. In this work, a deep guided attention network (DGAN) is presented for real image joint DN and DM (JDD), which considers both high SNR and high sampling rate of green information for DN and DM, respectively. To ease the training and fully exploit the data property of green channel, we first train DN and DM sub-networks sequentially and then learn them jointly, which can alleviate the error accumulation. Besides, in order to support the real image JDD, we collect paired raw clean RGB and noisy mosaic images to conduct a realistic dataset. The experimental results on real JDD dataset show the presented approach performs better than the state-of-the-art methods, in terms of both quantitative metrics and qualitative visualization.

show abstract

Section: Joint Denoising and Demosaicingmentioning

confidence: 99%

Deep Guided Attention Network for Joint Denoising and Demosaicing in Real Image

Zhang,

Fu,

Zhang

2024

Chinese J. Elect.

View full text Add to dashboard Cite

show abstract

“…They used this combined attention for feature selection while fusing features via skip connections to avoid noisy information in low layers. In [33], Fu et al proposed attention-based CNN to recover images not only contaminated by noise but also haze, blurring, and compression effects at the same time. They used double-pooling channel attention to merge maximum and average pooling layers.…”

Section: ) Attention Basedmentioning

confidence: 99%

MLFAN: Multilevel Feature Attention Network With Texture Prior for Image Denoising

2023

View full text Add to dashboard Cite

Machine learning techniques, especially deep learning, have made great achievements in computer vision including image denoising recently. However, in most convolutional neural network (CNN) based methods presented for image denoising, convolutional kernels are considered for only one scale and more scales are neglected mostly. Studies on multilevel feature extraction treat these features as if they have the same importance and do not use a mechanism such as feature attention for their weighting. Also, for effective noise removal, edge information is used as prior knowledge, but texture information is generally disregarded. This study has focused on these shortcomings and introduced a new attention-based CNN for image denoising. The main contributions of this study are as follows: First, we propose a CNN-based network to extract Local Binary Pattern (LBP) from the noisy image for texture information. So, we use texture information as prior knowledge for the preservation of details in the evolved image during the denoising process. Besides we propose a new multilevel feature extraction block to get different level features. After extracting multilevel features using feature attention, we weight these different levels of features. In addition to this, we introduce a multilevel feature attention network (MLFAN) for noise removal by combining them. The comprehensive experimental results show that our MLFAN noise reduction network can effectively remove Gaussian noise from images and compared with some stateof-the-art denoising methods, it outperforms in terms of both quantitative and qualitative evaluations. For Set12 grey image set, and McMaster color image set, MLFAN gives PSNR={33.

show abstract

“…Methods have been proposed to address various image-processing applications. For instance, Fu et al [31] proposed a multi-stage network for image restoration. One approach to train complex multi-stage networks is via ensemble learning.…”

Section: Deep Learning Modelmentioning

confidence: 99%

Gender Recognition Based on Gradual and Ensemble Learning from Multi-View Gait Energy Images and Poses

Leung,

Chan

2023

Sensors

View full text Add to dashboard Cite

Image-based gender classification is very useful in many applications, such as intelligent surveillance, micromarketing, etc. One common approach is to adopt a machine learning algorithm to recognize the gender class of the captured subject based on spatio-temporal gait features extracted from the image. The image input can be generated from the video of the walking cycle, e.g., gait energy image (GEI). Recognition accuracy depends on the similarity of intra-class GEIs, as well as the dissimilarity of inter-class GEIs. However, we observe that, at some viewing angles, the GEIs of both gender classes are very similar. Moreover, the GEI does not exhibit a clear appearance of posture. We postulate that distinctive postures of the walking cycle can provide additional and valuable information for gender classification. This paper proposes a gender classification framework that exploits multiple inputs of the GEI and the characteristic poses of the walking cycle. The proposed framework is a cascade network that is capable of gradually learning the gait features from images acquired in multiple views. The cascade network contains a feature extractor and gender classifier. The multi-stream feature extractor network is trained to extract features from the multiple input images. Features are then fed to the classifier network, which is trained with ensemble learning. We evaluate and compare the performance of our proposed framework with state-of-the-art gait-based gender classification methods on benchmark datasets. The proposed framework outperforms other methods that only utilize a single input of the GEI or pose.

show abstract

Multistage supervised contrastive learning for hybrid-degraded image restoration

Cited by 10 publications

References 30 publications

Deep Guided Attention Network for Joint Denoising and Demosaicing in Real Image

Deep Guided Attention Network for Joint Denoising and Demosaicing in Real Image

MLFAN: Multilevel Feature Attention Network With Texture Prior for Image Denoising

Gender Recognition Based on Gradual and Ensemble Learning from Multi-View Gait Energy Images and Poses

Contact Info

Product

Resources

About