A Feature-Enriched Deep Convolutional Neural Network for JPEG Image Compression Artifacts Reduction and its Applications

Chen, Honggang; He, Xiaohai; Yang, Hong; Qing, Linbo; Teng, Qizhi

doi:10.1109/tnnls.2021.3124370

Cited by 20 publications

(3 citation statements)

References 94 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compression artifacts affect the performance of computer vision tasks apart from decreasing visual quality [40], [43], [78]. In order to reduce the impact of compression artifacts, it may be helpful to suppress them during the preprocessing phase.…”

Section: Evaluations On Computer Vision Tasksmentioning

confidence: 99%

Reducing Image Compression Artifacts for Deep Neural Networks

Peng

Xing

et al. 2021

2021 Data Compression Conference (DCC)

View full text Add to dashboard Cite

With the benefit of deep learning techniques, recent researches have made significant progress in image compression artifacts reduction. Despite their improved performances, prevailing methods only focus on learning a mapping from the compressed image to the original one but ignore the intrinsic attributes of the given compressed images, which greatly harms the performance of downstream parsing tasks. Different from these methods, we propose to decouple the intrinsic attributes into two complementary features for artifacts reduction, i.e., the compression-insensitive features to regularize the high-level semantic representations during training and the compressionsensitive features to be aware of the compression degree. To achieve this, we first employ adversarial training to regularize the compressed and original encoded features for retaining high-level semantics, and we then develop the compression quality-aware feature encoder for compression-sensitive features. Based on these dual complementary features, we propose a Dual Awareness Guidance Network (DAGN) to utilize these awareness features as transformation guidance during the decoding phase. In our proposed DAGN, we develop a cross-feature fusion module to maintain the consistency of compression-insensitive features by fusing compression-insensitive features into the artifacts reduction baseline. Our method achieves an average 2.06 dB PSNR gains on BSD500, outperforming state-of-the-art methods, and only requires 29.7 ms to process one image on BSD500. Besides, the experimental results on LIVE1 and LIU4K also demonstrate the efficiency, effectiveness, and superiority of the proposed method in terms of quantitative metrics, visual quality, and downstream machine vision tasks.

show abstract

Section: Evaluations On Computer Vision Tasksmentioning

confidence: 99%

Reducing Image Compression Artifacts for Deep Neural Networks

Peng

Xing

et al. 2021

2021 Data Compression Conference (DCC)

View full text Add to dashboard Cite

show abstract

“…Huge arrays of numerical data are generated daily, which stimulates the development of information and computer technologies (Chen et al, 2022). Recently, neural network technology for data processing has become widespread.…”

Section: Introductionmentioning

confidence: 99%

An Efficient Training Algorithm of Restricted Boltzmann Machines

Matskevich¹

2023

European Proceedings of Computers and Technology

View full text Add to dashboard Cite

The paper deals with an actual applied problem related to the artificial neural networks training. An approach to the solution based on the idea of random search is proposed. An original training algorithm that implements Boltzmann annealing has been developed and its convergence in probability to the global optimum has been proved. It is also shown that the proposed algorithm can be easily modified to train any artificial neural network. Thus, it has a good prospect for solving applied problems using neural network technologies in general. Experimental studies have been carried out, in which, using the example of compressing color raster images problem, the proposed algorithm was compared with the known adaptive moment algorithm -one of the best gradient methods for training neural networks. Image compression was performed using an ensemble of n Gauss-Bernoulli restricted Boltzmann machines. The use of an ensemble of n machines in combination with a specially developed parallelization procedure made it possible to reduce the computational complexity of the training process and increase the speed of the proposed algorithm. As a result of experiments, it was shown that the proposed approach is not inferior to gradient methods in terms of speed. Moreover, the developed training algorithm turned out to be more than twice as effective as the adaptive moment algorithm in terms of the quality of the solution obtained.

show abstract

“…In the transform part, various deep learning-based networks have been developed to extract compact latent representations of the input image, such as residual blocks [6]- [8], attention modules [9], [10], invertible structures [11], or transformer blocks [12], [13]. Although these structures significantly improve the rate-distortion (RD) performance, their complexity of the networks is usually quite high.…”

Section: Introductionmentioning

confidence: 99%

Learned Image Compression with Inception Residual Blocks and Multi-Scale Attention Module

Liang

et al. 2022

2022 Picture Coding Symposium (PCS)

View full text Add to dashboard Cite

Deep learning-based image compression has made great progresses recently. However, many leading schemes use serial context-adaptive entropy model to improve the ratedistortion (R-D) performance, which is very slow. In addition, the complexities of the encoding and decoding networks are quite high and not suitable for many practical applications. In this paper, we introduce four techniques to balance the tradeoff between the complexity and performance. We are the first to introduce deformable convolutional module in compression framework, which can remove more redundancies in the input image, thereby enhancing compression performance. Second, we design an improved checkerboard context model with two separate distribution parameter estimation networks and different probability models, which enables parallel decoding without sacrificing the performance compared to the sequential contextadaptive model. Third, we develop a three-step knowledge distillation and training scheme to achieve different trade-offs between the complexity and the performance of the decoder network, which transfers both the final and intermediate results of the teacher network to the student network to help its training. Fourth, we introduce L1 regularization to make the numerical values of the latent representation more sparse. Then we only encode non-zero channels in the encoding and decoding process, which can greatly reduce the encoding and decoding time. Experiments show that compared to the state-of-the-art learned image coding scheme, our method can be about 20 times faster in encoding and 70-90 times faster in decoding, and our R-D performance is also 2.3% higher. Our method outperforms the traditional approach in H.266/VVC-intra (4:4:4) and some leading learned schemes in terms of PSNR and MS-SSIM metrics when testing on Kodak and Tecnick-40 datasets.

show abstract

A Feature-Enriched Deep Convolutional Neural Network for JPEG Image Compression Artifacts Reduction and its Applications

Cited by 20 publications

References 94 publications

Reducing Image Compression Artifacts for Deep Neural Networks

Reducing Image Compression Artifacts for Deep Neural Networks

An Efficient Training Algorithm of Restricted Boltzmann Machines

Learned Image Compression with Inception Residual Blocks and Multi-Scale Attention Module

Contact Info

Product

Resources

About