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

Convolutional Neural Network-Based Residue Super-Resolution for Video Coding

学校读者我要写书评

暂无评论

Convolutional Neural Network-Based Residue Super-Resolution ...

IEEE Visual Communications and Image processing (VCIP)

作者： Kang Liu Dong Liu Houqiang Li Feng Wu 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)9781538644591;9781538644584

Inspired by the progress of image and video super-resolution (SR) achieved by convolutional neural network (CNN), we propose a CNN-based residue SR method for video coding. Different from the previous works that operate in the pixel domain, i.e. down- and up-sampling of image or video frame, we propose to perform down- and up-sampling in the residue domain. Specifically, for each block, we perform motion estimation and compensation to achieve residual signal at the original resolution, then we down-sample the residue and compress it at low resolution, and perform residue SR using a trained CNN model. We design a new CNN for residue SR with the help of the motion compensated prediction signal. We integrate the residue SR method into the High Efficiency Video Coding (HEVC) scheme, providing mode decision at the level of coding tree unit. Experimental results show that our method achieves on average 4.0% and 2.8% BD-rate reduction under low-delay P and low-delay B configurations, respectively.

关键词： Encoding Signal resolution Video coding spatial resolution Delays Convolution

Generative Adversarial Network-Based Frame Extrapolation for Video Coding

学校读者我要写书评

暂无评论

Generative Adversarial Network-Based Frame Extrapolation for...

IEEE Visual Communications and Image processing (VCIP)

作者： Jianping Lin Dong Liu Houqiang Li Feng Wu 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)9781538644591;9781538644584

Motion estimation and motion compensation are fundamental in video coding to remove the temporal redundancy between video frames. The current video coding schemes usually adopt block-based motion estimation and compensation using simple translational or affine motion models, which cannot efficiently characterize complex motions in natural video signal. In this paper, we propose a frame extrapolation method for motion estimation and compensation. Specifically, based on the several previous frames, our method directly extrapolates the current frame using a trained deep network model. The deep network we adopted is a redesigned Video Coding oriented LAplacian Pyramid of Generative Adversarial Networks (VC-LAPGAN). The extrapolated frame is then used as an additional reference frame. Experimental results show that the VC-LAPGAN is capable in estimating and compensating for complex motions, and extrapolating frames with high visual quality. Using the VC-LAPGAN, our method achieves on average 2.0% BD-rate reduction than High Efficiency Video Coding (HEVC) under low-delay P configuration.

关键词： Video coding Motion estimation Training Computational modeling Extrapolation Laplace equations Convolutional codes

A CNN-Based In-Loop Filter with CU Classification for HEVC

学校读者我要写书评

暂无评论

A CNN-Based In-Loop Filter with CU Classification for HEVC

IEEE Visual Communications and Image processing (VCIP)

作者： Yuanying Dai Dong Liu Zheng-Jun Zha Feng Wu 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)9781538644591;9781538644584

Lossy compression of image and video yields visually annoying artifacts including blocking, blurring, ringing, etc., especially at low bit rates. In-loop filtering techniques can reduce these artifacts, improve quality, and achieve coding gain accordingly. In this paper, we present a convolutional neural network (CNN) based in-loop filter for High Efficiency Video Coding (HEVC). First, we design a new CNN structure that is composed of multiple Variable-filter-size Residue-learning blocks, namely VRCNN-ext, for artifact reduction. VRCNN-ext is trained by natural images as well as their compressed versions at different quality levels. Second, we investigate a new in-loop filter based on the trained VRCNN-ext models. Specifically, we observed that using VRCNN-ext directly on the inter pictures is not effective. To solve this problem, we further train a classifier to decide whether to use VRCNN-ext for each coding unit (CU). The classifier makes decision based on the compressed information, thus avoiding the overhead bits to control the on/off of the CNN-based filter at the CU level. Experimental results show that our scheme achieves significant bits saving than the HEVC anchor, leading to on average 9.2%, 9.6% and 7.4% BD-rate reduction on the HEVC test sequences, under all-intra, low-delay B and random-access configurations, respectively.

关键词： Decoding Encoding Training Image coding Feature extraction Copper Video coding

End-to-End Facial Image Compression with Integrated Semantic Distortion Metric

学校读者我要写书评

暂无评论

End-to-End Facial Image Compression with Integrated Semantic...

IEEE Visual Communications and Image processing (VCIP)

作者： Tianyu He 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)9781538644591;9781538644584

High efficient facial image compression is broadly required and challenging for surveillance and security scenarios, while either traditional general image codecs or special facial image compression schemes only heuristically refine codec separately according to face verification accuracy metric. We propose an End-to-End Facial Image Compression (E2EFIC) framework with a novel variable block size Regionally Adaptive Pooling (RAP) module whose parameters can be automatically optimized according to gradient feedback from an integrated semantic distortion metrics, including a successful exploration to apply Generative Adversarial Network (GAN) as metric directly in image compression scheme. The experimental results verify the framework's efficiency by demonstrating performance improvement of 71.41%, 48.28% and 52.67% bitrate saving separately over JPEG2000, WebP and neural network-based codecs under the same face verification accuracy distortion metric. We also evaluate E2EFIC's superior performance gain compared with latest specific facial image codecs.

关键词： Image coding Distortion Semantics Face Bit rate Codecs

An end-to-end foreground-aware network for person re-identification

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Liu, Yiheng Zhou, Wengang Liu, Jianzhuang Qi, Guojun Tian, Qi 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 Noah’s Ark Lab Huawei Technologies Company Limited Shenzhen518129 China Huawei Cloud EI Product Department Cloud & AI Huawei Technologies

Person re-identification is a crucial task of identifying pedestrians of interest across multiple surveillance camera views. For person re-identification, a pedestrian is usually represented with features extracted from a rectangular image region that inevitably contains the scene background, which incurs ambiguity to distinguish different pedestrians and degrades the accuracy. Thus, we propose an end-to-end foreground-aware network to discriminate against the foreground from the background by learning a soft mask for person re-identification. In our method, in addition to the pedestrian ID as supervision for the foreground, we introduce the camera ID of each pedestrian image for background modeling. The foreground branch and the background branch are optimized collaboratively. By presenting a target attention loss, the pedestrian features extracted from the foreground branch become more insensitive to backgrounds, which greatly reduces the negative impact of changing backgrounds on pedestrian matching across different camera views. Notably, in contrast to existing methods, our approach does not require an additional dataset to train a human landmark detector or a segmentation model for locating the background regions. The experimental results conducted on three challenging datasets, i.e., Market-1501, DukeMTMC-reID, and MSMT17, demonstrate the effectiveness of our approach. Copyright © 2019, The Authors. All rights reserved.

关键词： Cameras

Classification of Large-Scale High-Resolution SAR Images with Deep Transfer Learning

学校读者我要写书评

暂无评论

TechRxiv

TechRxiv 2019年

作者： Huang, Zhongling Dumitru, Corneliu Octavian Pan, Zongxu Lei, Bin Datcu, Mihai The Aerospace Information Research Institute Chinese Academy of Sciences Beijing100094 China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Huairou District Beijing101408 China Key Laboratory of Technology in Geo-spatial Information Processing and Application System Chinese Academy of Sciences Beijing China Wessling 82234 Germany

The classification of large-scale high-resolution SAR land cover images acquired by satellites is a challenging task, facing several difficulties such as semantic annotation with expertise, changing data characteristics due to varying imaging parameters or regional target area differences, and complex scattering mechanisms being different from optical imaging. Given a large-scale SAR land cover dataset collected from TerraSAR-X images with a hierarchical three-level annotation of 150 categories and comprising more than 100,000 patches, three main challenges in automatically interpreting SAR images of highly imbalanced classes, geographic diversity, and label noise are addressed. In this letter, a deep transfer learning method is proposed based on a similarly annotated optical land cover dataset (NWPU-RESISC45). Besides, a top-2 smooth loss function with cost-sensitive parameters was introduced to tackle the label noise and imbalanced classes’ problems. The proposed method shows high efficiency in transferring information from a similarly annotated remote sensing dataset, a robust performance on highly imbalanced classes, and is alleviating the over-fitting problem caused by label noise. What’s more, the learned deep model has a good generalization for other SAR-specific tasks, such as MSTAR target recognition with a state-of-the-art classification accuracy of 99.46%. © 2019, CC BY.

关键词： Synthetic aperture radar

What, Where and How to Transfer in SAR Target Recognition Based on Deep CNNs

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Huang, Zhongling Pan, Zongxu Lei, Bin School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Huairou District Beijing101408 China Key Laboratory of Technology in Geo-spatial Information Processing and Application System Chinese Academy of Sciences Beijing100190 China Institute of Electronics Chinese Academy of Sciences Beijing100190 China

Deep convolutional neural networks (DCNNs) have attracted much attention in remote sensing recently. Compared with the large-scale annotated dataset in natural images, the lack of labeled data in remote sensing becomes an obstacle to train a deep network very well, especially in SAR image interpretation. Transfer learning provides an effective way to solve this problem by borrowing the knowledge from the source task to the target task. In optical remote sensing application, a prevalent mechanism is to fine-tune on an existing model pre-trained with a large-scale natural image dataset, such as ImageNet. However, this scheme does not achieve satisfactory performance for SAR application because of the prominent discrepancy between SAR and optical images. In this paper, we attempt to discuss three issues that are seldom studied before in detail: (1) what network and source tasks are better to transfer to SAR targets, (2) in which layer are transferred features more generic to SAR targets and (3) how to transfer effectively to SAR targets recognition. Based on the analysis, a transitive transfer method via multi-source data with domain adaptation is proposed in this paper to decrease the discrepancy between the source data and SAR targets. Several experiments are conducted on OpenSARShip. The results indicate that the universal conclusions about transfer learning in natural images cannot be completely applied to SAR targets, and the analysis of what and where to transfer in SAR target recognition is helpful to decide how to transfer more effectively. Copyright © 2019, The Authors. All rights reserved.

关键词： Deep neural networks

Learning for video compression

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Chen, Zhibo He, Tianyu Jin, Xin Wu, Feng CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China

One key challenge to learning-based video compression is that motion predictive coding, a very effective tool for video compression, can hardly be trained into a neural network. In this paper we propose the concept of PixelMotionCNN (PMCNN) which includes motion extension and hybrid prediction networks. PMCNN can model spatiotemporal coherence to effectively perform predictive coding inside the learning network. On the basis of PMCNN, we further explore a learning-based framework for video compression with additional components of iterative analysis/synthesis, binarization, etc. Experimental results demonstrate the effectiveness of the proposed scheme. Although entropy coding and complex configurations are not employed in this paper, we still demonstrate superior performance compared with MPEG-2 and achieve comparable results with H.264 codec. The proposed learning-based scheme provides a possible new direction to further improve compression efficiency and functionalities of future video coding. Copyright © 2018, The Authors. All rights reserved.

关键词： Image compression