检索结果-内蒙古大学图书馆

LEARNED SCALABLE IMAGE COMPRESSION WITH BIDIRECTIONAL CONTEXT DISENTANGLEMENT NETWORK

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Zhang, Zhizheng Chen, Zhibo Lin, Jianxin Li, Weiping CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei China

In this paper, we propose a learned scalable/progressive image compression scheme based on deep neural networks (DNN), named Bidirectional Context Disentanglement Network (BCD-Net). For learning hierarchical representations, we first adopt bit-plane decomposition to decompose the information coarsely before the deep-learning-based transformation. However, the information carried by different bit-planes is not only unequal in entropy but also of different importance for reconstruction. We thus take the hidden features corresponding to different bit-planes as the context and design a network topology with bidirectional flows to disentangle the contextual information for more effective compressed representations. Our proposed scheme enables us to obtain the compressed codes with scalable rates via a one-pass encoding-decoding. Experiment results demonstrate that our proposed model outperforms the state-of-the-art DNN-based scalable image compression methods in both PSNR and MS-SSIM metrics. In addition, our proposed model achieves better performance in MS-SSIM metric than conventional scalable image codecs. Effectiveness of our technical components is also verified through sufficient ablation experiments. Copyright © 2018, The Authors. All rights reserved.

关键词： Deep neural networks

SIFT-preserving compression of mobile-captured license plate images for recognition

学校读者我要写书评

暂无评论

SIFT-preserving compression of mobile-captured license plate...

International Conference on Wireless Communications and Signal processing (WCSP)

作者： Dandan Wang Dong Liu CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei China

ISBN: (纸本)9781479973408

Image compression had been extensively studied for reducing coding rate yet producing acceptable visual quality. However, there are many application scenarios where the compressed images are used for automatic recognition rather than human viewing, thus the visual quality is no longer critical for compression. SIFT features have demonstrated their utility in many recognition scenarios and SIFT-preserving compression is developed recently. In this paper, we firstly study the SIFT-preserving compression of license plate images for recognition accuracy rather than visual quality. According to extracted SIFT features, each image is divided into SIFT coding-units and non-SIFT coding-units. Each coding-unit is assigned with a different quality parameter when using JPEG for compression. We compare our proposed scheme with the standard JPEG that uses a unified quality parameter. Experimental results with manually tuned parameters show that on average 14% bit-rate can be saved by our scheme, without any loss of recognition accuracy.

关键词： Image coding Transform coding Licenses Standards Image recognition Feature extraction Accuracy

Deep Scalable Image Compression via Hierarchical Feature Decorrelation

学校读者我要写书评

暂无评论

Deep Scalable Image Compression via Hierarchical Feature Dec...

Picture Coding Symposium, PCS

作者： Zongyu Guo Zhizheng Zhang Zhibo Chen CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei China

The following topics are dealt with: video coding; data compression; image coding; convolutional neural nets; decoding; learning (artificial intelligence); motion compensation; video codecs; image reconstruction; filt...

关键词：

Analyzing Time Complexity of Practical Learned Image Compression Models

学校读者我要写书评

暂无评论

Analyzing Time Complexity of Practical Learned Image Compres...

IEEE Visual Communications and Image processing (VCIP)

作者： Xiaohan Pan Zongyu Guo Zhibo Chen CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei China

ISBN: (纸本)9781728173221

We have witnessed the rapid development of learned image compression (LIC). The latest LIC models have outperformed almost all traditional image compression standards in terms of rate-distortion (RD) performance. However, the time complexity of LIC model is still underdiscovered, limiting the practical applications in industry. Even with the acceleration of GPU, LIC models still struggle with long coding time, especially on the decoder side. In this paper, we analyze and test a few prevailing and representative LIC models, and compare their complexity with traditional codecs including H.265/HEVC intra and H.266/VVC intra. We provide a comprehensive analysis on every module in the LIC models, and investigate how bitrate changes affect coding time. We observe that the time complexity bottleneck mainly exists in entropy coding and context modelling. Although this paper pay more attention to experimental statistics, our analysis reveals some insights for further acceleration of LIC model, such as model modification for parallel computing, model pruning and a more parallel context model.

关键词： Analytical models Image coding Codecs Visual communication Computational modeling Rate-distortion Decoding

Extent and spatial distribution of terrace abandonment in China

学校读者我要写书评

暂无评论

Journal of Geographical Sciences 2023年第7期33卷 1361-1376页

作者： DONG Shijie XIN Liangjie LI Shengfa XIE Hualin ZHAO Yuluan WANG Xue LI Xiubin SONG Hengfei LU Yahan Key Laboratory of Land Surface Pattern and Simulation Institute of Geographic Sciences and Natural Resources ResearchCASBeijing 100101China University of Chinese Academy of Sciences Beijing 100049China Key Lab of Guangdong for Utilization of Remote Sensing and Geographical Information System/Guangdong Open Laboratory of Geospatial Information Technology and Application Guangzhou Institute of GeographyGuangdong Academy of SciencesGuangzhou 510070China Institute of Ecological Civilization Jiangxi University of Finance and EconomicsNanchang 330013China College of Geography and Environmental Science Guizhou Normal UniversityGuiyang 550001China

Driven by urbanization and industrialization,arable land in hilly and mountainous regions of China is gradually becoming marginalized,with the extent of arable land abandonment rapidly expanding from poor-quality sloping arable land to high-quality *** abandonment of large-scale terraces will lead to a series of socio-economic and ecological effects.A national sample survey was used to investigate the extent and spatial distribution of terrace abandonment in China,and a total of 560 valid village questionnaires from 329 counties were collected in the mountainous areas of *** main findings are as follows:(1)The phenomenon of terrace abandonment was widespread throughout the country,with 54% of the total surveyed villages exhibiting terrace abandonment,and the area of abandoned terraces accounting for 9.79% of the total.(2) The degree of terrace abandonment is high in the south and low in the *** most serious region with abandonment was the hilly and mountainous areas in the south,especially in the middle and lower Yangtze River region.(3)The main driving factors of terrace abandonment were rural labor migration,agricultural mechanization level,irrigation conditions,and transportation conditions for *** measures should be taken based on the specific conditions of each area to alleviate terrace *** such as improving terrace mechanization are universally ***,low-quality terraces can be withdrawn orderly,and for high-quality terraces,multiple measures are needed to consolidate agricultural production,such as adjusting the planting structure,strengthening agricultural infrastructure construction,and encouraging the transfer of land-use rights as well as large-scale operation.

关键词： terraces arable land abandonment national sample survey spatial variation China

MACHINE LEARNING-BASED MULTI-CHANNEL EVALUATION POOLING STRATEGY FOR IMAGE QUALITY ASSESSMENT

学校读者我要写书评

暂无评论

MACHINE LEARNING-BASED MULTI-CHANNEL EVALUATION POOLING STRA...

IEEE International Conference on Image processing

作者： Anzhou Hu Rong Zhang Dong Yin Wenlong Hu Department of Electronic Engineering and Information Science University of Science and Technology of China Key Laboratory of Geospatial Information Processing and Application System Technology Chinese Academy of Sciences

ISBN: (纸本)9781479923427

Multi-channel peculiarity is one of the most widely accepted human visual system (HVS) models for perceptual image quality assessment (IQA). Otherwise than extensive studies of channel decomposition and intra-channel distortion measure, relatively scant research effort has been devoted to develop efficient multichannel evaluation pooling strategies. In this paper, we review and address the limitations of the conventional pooling models based on HVS sensitivities-weighted average. Instead, we explore the utilization of machine learning for this pooling problem, since machine learning can establish an optimal and generalized mapping that models the highly complex relationship between the multi-channel distortion evaluations and the perceived image quality. Experiments based on available subjective IQA databases demonstrate the rationality, reliability and robustness of our proposed scheme.

关键词： Image quality assessment (IQA) Multi-channel model Evaluation pooling Machine learning

A coarse-to-fine framework for learned color enhancement with non-local attention

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Shan, Chaowei Zhang, Zhizheng Chen, Zhibo CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China

Automatic color enhancement is aimed to adaptively adjust photos to expected styles and tones. For current learned methods in this field, global harmonious perception and local details are hard to be well-considered in a single model simultaneously. To address this problem, we propose a coarse-tofine framework with non-local attention for color enhancement in this paper. Within our framework, we propose to divide enhancement process into channel-wise enhancement and pixel-wise refinement performed by two cascaded Convolutional Neural Networks (CNNs). In channel-wise enhancement, our model predicts a global linear mapping for RGB channels of input images to perform global style adjustment. In pixel-wise refinement, we learn a refining mapping using residual learning for local adjustment. Further, we adopt a non-local attention block to capture the long-range dependencies from global information for subsequent fine-grained local refinement. We evaluate our proposed framework on the commonly using benchmark and conduct sufficient experiments to demonstrate each technical component within it. Copyright © 2019, The Authors. All rights reserved.

关键词： Pixels

FreqAlign: Excavating Perception-oriented Transferability for Blind Image Quality Assessment from A Frequency Perspective

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Li, Xin Lu, Yiting Chen, Zhibo The CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China

Blind Image Quality Assessment (BIQA) is susceptible to poor transferability when the distribution shift occurs, e.g., from synthesis degradation to authentic degradation. To mitigate this, some studies have attempted to design unsupervised domain adaptation (UDA) based schemes for BIQA, which intends to eliminate the domain shift through adversarial-based feature alignment. However, the feature alignment is usually taken at the low-frequency space of features since the global average pooling operation. This ignores the transferable perception knowledge in other frequency components and causes the sub-optimal solution for the UDA of BIQA. To overcome this, from a novel frequency perspective, we propose an effective alignment strategy, i.e., Frequency Alignment (dubbed FreqAlign), to excavate the perception-oriented transferability of BIQA in the frequency space. Concretely, we study what frequency components of features are more proper for perception-oriented alignment. Based on this, we propose to improve the perception-oriented transferability of BIQA by performing feature frequency decomposition and selecting the frequency components that contained the most transferable perception knowledge for alignment. To achieve a stable and effective frequency selection, we further propose the frequency movement with a sliding window to find the optimal frequencies for alignment, which is composed of three strategies, i.e., warm up with pre-training, frequency movement-based selection, and perturbation-based finetuning. Extensive experiments under different domain adaptation settings of BIQA have validated the effectiveness of our proposed method. The code will be released at https://***/lixinustc/Openworld-IQA. Copyright © 2023, The Authors. All rights reserved.

关键词： Alignment

Learning omni-frequency region-adaptive representations for real image super-resolution

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Li, Xin Jin, Xin Yu, Tao Pang, Yingxue Sun, Simeng Zhang, Zhizheng Chen, Zhibo CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China

Traditional single image super-resolution (SISR) methods that focus on solving single and uniform degradation (i.e., bicubic down-sampling), typically suffer from poor performance when applied into real-world low-resolution (LR) images due to the complicated realistic degradations. The key to solving this more challenging real image super-resolution (RealSR) problem lies in learning feature representations that are both informative and content-aware. In this paper, we propose an Omni-frequency Region-adaptive Network (OR-Net) to address both challenges, here we call features of all low, middle and high frequencies omni-frequency features. Specifically, we start from the frequency perspective and design a Frequency Decomposition (FD) module to separate different frequency components to comprehensively compensate the information lost for real LR image. Then, considering the different regions of real LR image have different frequency information lost, we further design a Region-adaptive Frequency Aggregation (RFA) module by leveraging dynamic convolution and spatial attention to adaptively restore frequency components for different regions. The extensive experiments endorse the effective, and scenario-agnostic nature of our OR-Net for RealSR. Copyright © 2020, The Authors. All rights reserved.

关键词： Optical resolving power