检索结果-内蒙古大学图书馆

Efficient Integer-Arithmetic-Only Convolutional Networks with Bounded ReLU

学校读者我要写书评

暂无评论

Efficient Integer-Arithmetic-Only Convolutional Networks wit...

IEEE International Symposium on Circuits and systems (ISCAS)

作者： Hengrui Zhao Dong Liu Houqiang Li CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei China

To facilitate large-scale deployment of convolutional networks, integer-arithmetic-only inference has been demonstrated effective, which not only reduces computational cost but also ensures cross-platform consistency. However, previous studies on integer networks usually report a decline in the inference accuracy, given the same number of parameters as floating-point-number (FPN) networks. In this paper, we propose to finetune and quantize a well-trained FPN convolutional network to obtain an integer convolutional network. Our key idea is to adjust the upper bound of a bounded rectified linear unit (ReLU), which replaces the normal ReLU and effectively controls the dynamic range of activations. Based on the tradeoff between learning ability and quantization error of networks, we managed to preserve full accuracy after quantization and obtain efficient integer networks. Our experiments on ResNet for image classification demonstrate that our 8-bit integer networks achieve state-of-the-art performance compared with Google's TensorFlow and NVIDIA's TensorRT. Moreover, we experiment on VDSR for image super-resolution and on VRCNN for compression artifact reduction, both of which serve regression tasks that natively require high inference accuracy. Besides ensuring the equivalent performance as the corresponding FPN networks, our integer networks have only 1/4 memory cost and run 2× faster on GPUs.

关键词： Upper bound Quantization (signal) Image coding Superresolution Dynamic range Task analysis Image classification

360HRL: Hierarchical Reinforcement Learning Based Rate Adaptation for 360-Degree Video Streaming

学校读者我要写书评

暂无评论

360HRL: Hierarchical Reinforcement Learning Based Rate Adapt...

IEEE Visual Communications and Image processing (VCIP)

作者： Jun Fu Chen Hou 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

Recently, reinforced adaptive bitrate (ABR) algorithms have achieved remarkable success in tile-based 360-degree video streaming. However, they heavily rely on accurate viewport prediction. To alleviate this issue, we propose a hierarchical reinforcement-learning (RL) based ABR algorithm, dubbed 360HRL. Specifically, 360HRL consists of a top agent and a bottom agent. The former is used to decide whether to download a new segment for continuous playback or re-download an old segment for correcting wrong bitrate decisions caused by inaccurate viewport estimation, and the latter is used to select bitrates for tiles in the chosen segment. In addition, 360HRL adopts a two-stage training methodology. In the first stage, the bottom agent is trained under the environment where the top agent always chooses to download a new segment. In the second stage, the bottom agent is fixed and the top agent is optimized with the help of a heuristic decision rule. Experimental results demonstrate that 360HRL outperforms existing RL-based ABR algorithms across a broad of network conditions and quality of experience (QoE) objectives.

关键词： Training Visual communication Image processing Bit rate Estimation Reinforcement learning Streaming media

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

Spatiotemporal analysis of COVID-19 risk in Guangdong Province based on population migration

学校读者我要写书评

暂无评论

Journal of Geographical Sciences 2020年第12期30卷 1985-2001页

作者： YE Yuyao WANG Changjian ZHANG Hong'ou YANG Ji LIU Zhengqian WU Kangmin DENG Yingbin Key Lab of Guangdong for Utilization of Remote Sensing and Geographical Information System Guangdong Open Laboratory of Geospatial Information Technology and ApplicationGuangzhou Institute of GeographyGuangdong Academy of SciencesGuangzhou 510070China Southern Marine Science and Engineering Guangdong Laboratory Guangzhou 511458China School of Architecture and Urban Planning Guangdong University of TechnologyGuangzhou 510090China

Population migration,especially population inflow from epidemic areas,is a key source of the risk related to the coronavirus disease 2019(COVID-19)*** paper selects Guangdong Province,China,for a case *** utilizes big data on population migration and the geospatial analysis technique to develop a model to achieve spatiotemporal analysis of COVID-19 *** model takes into consideration the risk differential between the source cities of population migration as well as the heterogeneity in the socioeconomic characteristics of the destination cities of population *** further incorporates a time-lag process based on the time distribution of the onset of the imported *** theory,the model will be able to predict the evolutional trend and spatial distribution of the COVID-19 risk for a certain time period in the future and provide support for advanced planning and targeted prevention *** research findings indicate the following:(1)The COVID-19 epidemic in Guangdong Province reached a turning point on January 29,2020,after which it showed a gradual decreasing trend.(2)Based on the time-lag analysis of the onset of the imported cases,it is common fora time interval to exist between case importation and illness onset,and the proportion of the cases with an interval of 1-14 days is relatively high.(3)There is evident spatial heterogeneity in the epidemic risk;the risk varies significantly between different areas based on their imported risk,susceptibility risk,and ability to prevent the spread.(4)The degree of connectedness and the scale of population migration between Guangdong’s prefecture-level cities and their counterparts in the source regions of the epidemic,as well as the transportation and location factors of the cities in Guangdong,have a significant impact on the risk classification of the cities in *** first-tier cities-Shenzhen and Guangzhou-are high-risk *** cities in the Pearl River Delta that are adjacent

关键词： population migration COVID-19 epidemic risk time-lag process spatiotemporal analysis

Domain-class correlation decomposition for generalizable person re-identification

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Yang, Kaiwen Tian, Xinmei CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China

Domain generalization in person re-identification is a highly important meaningful and practical task in which a model trained with data from several source domains is expected to generalize well to unseen target domains. Domain adversarial learning is a promising domain generalization method that aims to remove domain information in the latent representation through adversarial training. However, in person re-identification, the domain and class are correlated, and we theoretically show that domain adversarial learning will lose certain information about class due to this domain-class correlation. Inspired by casual inference, we propose to perform interventions to the domain factor d, aiming to decompose the domain-class correlation. To achieve this goal, we proposed estimating the resulting representation z∗ caused by the intervention through first- and second-order statistical characteristic matching. Specifically, we build a memory bank to restore the statistical characteristics of each domain. Then, we use the newly generated samples {z∗, y, d∗} to compute the loss function. These samples are domain-class correlation decomposed;thus, we can learn a domain-invariant representation that can capture more class-related features. Extensive experiments show that our model outperforms the state-of-the-art methods on the large-scale domain generalization Re-ID benchmark. Copyright © 2021, The Authors. All rights reserved.

关键词： Machine learning

aiWave: Volumetric Image Compression with 3-D Trained Affine Wavelet-like Transform

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Xue, Dongmei Ma, Haichuan Li, Li Liu, Dong Xiong, Zhiwei The CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China The Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei230088 China

Volumetric image compression has become an urgent task to effectively transmit and store images produced in biological research and clinical practice. At present, the most commonly used volumetric image compression methods are based on wavelet transform, such as JP3D. However, JP3D employs an ideal, separable, global, and fixed wavelet basis to convert input images from pixel domain to frequency domain, which seriously limits its performance. In this paper, we first design a 3-D trained wavelet-like transform to enable signal-dependent and non-separable transform. Then, an affine wavelet basis is introduced to capture the various local correlations in different regions of volumetric images. Furthermore, we embed the proposed wavelet-like transform to an end-to-end compression framework called aiWave to enable an adaptive compression scheme for various datasets. Last but not least, we introduce the weight sharing strategies of the affine wavelet-like transform according to the volumetric data characteristics in the axial direction to reduce the number of parameters. The experimental results show that: 1) when cooperating our trained 3-D affine wavelet-like transform with a simple factorized entropy coding module, aiWave performs better than JP3D and is comparable in terms of encoding and decoding complexities;2) when adding a context module to remove signal redundancy further, aiWave can achieve a much better performance than HEVC. Copyright © 2022, The Authors. All rights reserved.

关键词： Image compression

Attribute Artifacts Removal for Geometry-based Point Cloud Compression

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Sheng, Xihua Li, Li Liu, Dong Xiong, Zhiwei CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China

Geometry-based point cloud compression (G-PCC) can achieve remarkable compression efficiency for point clouds. However, it still leads to serious attribute compression artifacts, especially under low bitrate scenarios. In this paper, we propose a Multi-Scale Graph Attention Network (MS-GAT) to remove the artifacts of point cloud attributes compressed by G-PCC. We first construct a graph based on point cloud geometry coordinates and then use the Chebyshev graph convolutions to extract features of point cloud attributes. Considering that one point may be correlated with points both near and far away from it, we propose a multi-scale scheme to capture the short- and long-range correlations between the current point and its neighboring and distant points. To address the problem that various points may have different degrees of artifacts caused by adaptive quantization, we introduce the quantization step per point as an extra input to the proposed network. We also incorporate a weighted graph attentional layer into the network to pay special attention to the points with more attribute artifacts. To the best of our knowledge, this is the first attribute artifacts removal method for G-PCC. We validate the effectiveness of our method over various point clouds. Objective comparison results show that our proposed method achieves an average of 9.74% BD-rate reduction compared with Predlift and 10.13% BD-rate reduction compared with RAHT. Subjective comparison results present that visual artifacts such as color shifting, blurring, and quantization noise are reduced. Copyright © 2021, The Authors. All rights reserved.

关键词： Convolution

LIQA: Lifelong blind image quality assessment

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Liu, Jianzhao Zhou, Wei Xu, Jiahua Li, Xin An, Shukun Chen, Zhibo CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China

Existing blind image quality assessment (BIQA) methods are mostly designed in a disposable way and cannot evolve with unseen distortions adaptively, which greatly limits the deployment and application of BIQA models in real-world scenarios. To address this problem, we propose a novel Lifelong blind Image Quality Assessment (LIQA) approach, targeting to achieve the lifelong learning of BIQA. Without accessing to previous training data, our proposed LIQA can not only learn new distortions, but also mitigate the catastrophic forgetting of seen distortions. Specifically, we adopt the Split-and-Merge distillation strategy to train a single-head network that makes task-agnostic predictions. In the split stage, we first employ a distortion-specific generator to obtain the pseudo features of each seen distortion. Then, we use an auxiliary multi-head regression network to generate the predicted quality of each seen distortion. In the merge stage, we replay the pseudo features paired with pseudo labels to distill the knowledge of multiple heads, which can build the final regressed single head. Experimental results demonstrate that the proposed LIQA method can handle the continuous shifts of different distortion types and even datasets. More importantly, our LIQA model can achieve stable performance even if the task sequence is long. Copyright © 2021, The Authors. All rights reserved.

关键词： Distillation

DouZero+: Improving DouDizhu AI by Opponent Modeling and Coach-guided Learning

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhao, Youpeng Zhao, Jian Hu, Xunhan Zhou, Wengang Li, Houqiang CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System Department of Electronic Engineering and Information Science University of Science and Technology of China Hefei230027 China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei China

Recent years have witnessed the great breakthrough of deep reinforcement learning (DRL) in various perfect and imperfect information games. Among these games, DouDizhu, a popular card game in China, is very challenging due to the imperfect information, large state space, elements of collaboration and a massive number of possible moves from turn to turn. Recently, a DouDizhu AI system called DouZero has been proposed. Trained using traditional Monte Carlo method with deep neural networks and self-play procedure without the abstraction of human prior knowledge, DouZero has outperformed all the existing DouDizhu AI programs. In this work, we propose to enhance DouZero by introducing opponent modeling into DouZero. Besides, we propose a novel coach network to further boost the performance of DouZero and accelerate its training process. With the integration of the above two techniques into DouZero, our DouDizhu AI system achieves better performance and ranks top in the Botzone leaderboard among more than 400 AI agents, including DouZero. Copyright © 2022, The Authors. All rights reserved.

关键词： Reinforcement learning