检索结果-内蒙古大学图书馆

Interpreting the Latent Space of GANs via Correlation Analysis for Controllable Concept Manipulation

学校读者我要写书评

暂无评论

Interpreting the Latent Space of GANs via Correlation Analys...

International Conference on Pattern Recognition

作者： Ziqiang Li Rentuo Tao Hongjing Niu Mingdao Yue Bin Li CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application Systems University of Science and Technology of China Hefei Anhui China College of Mechanical and Electrical Engineering Suzhou University Suzhou Anhui China

Generative adversarial nets (GANs) have been successfully applied in many fields like image generation, inpainting, super-resolution, and drug discovery, etc. By now, the inner process of GANs is far from being understood. To get a deeper insight into the intrinsic mechanism of GANs, in this paper, a method for interpreting the latent space of GANs by analyzing the correlation between latent variables and the corresponding semantic contents in generated images is proposed. Unlike previous methods that focus on dissecting models via feature visualization, the emphasis of this work is put on the variables in latent space, i.e. how the latent variables affect the quantitative analysis of generated results. Given a pre-trained GAN model with weights fixed, the latent variables are intervened to analyze their effect on the semantic content in generated images. A set of controlling latent variables can be derived for specific content generation, and the controllable semantic content manipulation is achieved. The proposed method is testified on the datasets Fashion-MNIST and UT Zappos50K, experiment results show its effectiveness.

关键词： Drugs Visualization Analytical models Correlation Statistical analysis Image synthesis Semantics

Efficient Gridless DoA Estimation Method of Non-uniform Linear Arrays with Applications in Automotive Radars

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Gao, Silin Zhang, Zhe Wang, Muhan Zhang, Yan Zhao, Jie Zhang, Bingchen Wang, Yue Wu, Yirong Aerospace Information Research Institute Chinese Academy of Sciences Beijing China Key Laboratory of Technology in Geo-spatial Information Processing and Application System Chinese Academy of Sciences Beijing China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing China Suzhou Key Laboratory of Microwave Imaging Processing and Application Technology Suzhou Aerospace Information Research Institute Jiangsu Suzhou China The Beijing Autoroad Tech Co. Ltd China Electrical and Computer Engineering Department George Mason University FairfaxVA United States

This paper focuses on the gridless direction-of-arrival (DoA) estimation for data acquired by non-uniform linear arrays (NLAs) in automotive applications. Atomic norm minimization (ANM) is a promising gridless sparse recovery algorithm under the Toeplitz model and solved by convex relaxation, thus it is only applicable to uniform linear arrays (ULAs) with array manifolds having a Vandermonde structure. In automotive applications, it is essential to apply the gridless DoA estimation to NLAs with arbitrary geometry with efficiency. In this paper, a fast ANM-based gridless DoA estimation algorithm for NLAs is proposed, which employs the array manifold separation technique and the accelerated proximal gradient (APG) technique, making it applicable to NLAs without losing of efficiency. Simulation and measurement experiments on automotive multiple-input multiple-outpt (MIMO) radars demonstrate the superiority of the proposed method. Copyright © 2023, The Authors. All rights reserved.

关键词： Efficiency

Self-guided Few-shot Semantic Segmentation for Remote Sensing Imagery Based on Large Vision Models

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Qi, Xiyu Wu, Yifan Mao, Yongqiang Zhang, Wenhui Zhang, Yidan Aerospace Information Research Institute Chinese Academy of Sciences Beijing100190 China Aerospace Information Research Institute Chinese Academy of Sciences Beijing100190 China Key Laboratory of Technology in Geo-Spatial Information Processing and Application System Aerospace Information Research Institute Chinese Academy of Sciences Beijing100190 China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing100190 China

The Segment Anything Model (SAM) exhibits remarkable versatility and zero-shot learning abilities, owing largely to its extensive training data (SA-1B). Recognizing SAM's dependency on manual guidance given its category-agnostic nature, we identified unexplored potential within few-shot semantic segmentation tasks for remote sensing imagery. This research introduces a structured framework designed for the automation of few-shot semantic segmentation. It utilizes the SAM model and facilitates a more efficient generation of semantically discernible segmentation outcomes. Central to our methodology is a novel automatic prompt learning approach, leveraging prior guided mask to produce coarse pixel-wise prompts for SAM. Extensive experiments on the DLRSD datasets underlines the superiority of our approach, outperforming other available few-shot methodologies. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantic Segmentation

Analysis of the Reconstruction Accuracy of Compact Polarized SAR Pseudo Quad-Pol Data for Use in Ocean Surface Observations

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Wang, Xiaochen Hu, Yuxin Han, Bing Duan, Jitong Aerospace Information Research Institute Chinese Academy of Science Beijing100190 China Key Laboratory of Technology in Geo-spatial Information Processing and Application Systems Aerospace Information Research Institute Chinese Academy of Science Beijing100190 China Deqing Academy of Satellite Application Huzhou313200 China

This paper assesses the capability of Compact Polarized (CP) Synthetic Aperture Radar (SAR) to explore ocean surface backscattering by reconstructing the pseudo quad-pol data. Besides using Souyris’s or Nord’s algorithms, 8 scenes of Radarsat-2 quad-polarized images are used to develop an empirical model for estimating the initial value of N in Collins’ algorithm. The robustness the three published algorithms are discussed together with the reconstruction error of polarization scattering matrix [S]. The comparisons show that Collins’ algorithm is superior to the other two algorithms in terms of reconstruction errors for the hh, vv, especially, the hv channels. In addition, the influence of each algorithm on polarimetric parameters is investigated. Based on the retrieval of the polarimetric parameters, it is concluded that Souyris’s, Nord’s and Collins’ algorithms all have similar (high) accuracies for co-polarization backscattering coefficient σ0HH, σ0VV, co-polarization correlation coefficient ρ and first eigenvalue l1, while for cross-polarization backscattering coefficient σ0HV and scattering angle α, the accuracy of Collins’ algorithm is better than that of Souyris’s or Nord’s’. Although all three algorithms produced low accuracies for second eigenvalue l2, third eigenvalue l3, scattering entropy H and scattering anisotropy A, the results obtained using Collins’ algorithm were better than those produced by the other two algorithms. © 2022, The Authors. All rights reserved.

关键词： Synthetic aperture radar

3-D Context Entropy Model for Improved Practical Image Compression

学校读者我要写书评

暂无评论

3-D Context Entropy Model for Improved Practical Image Compr...

IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

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

ISBN: (数字)9781728193601

ISBN: (纸本)9781728193618

In this paper, we present our image compression framework designed for CLIC 2020 competition. Our method is based on Variational AutoEncoder (VAE) architecture which is strengthened with residual structures. In short, we make three noteworthy improvements here. First, we propose a 3-D context entropy model which can take advantage of known latent representation in current spatial locations for better entropy estimation. Second, a light-weighted residual structure is adopted for feature learning during entropy estimation. Finally, an effective training strategy is introduced for practical adaptation with different resolutions. Experiment results indicate our image compression method achieves 0.9775 MS-SSIM on CLIC validation set and 0.9809 MS-SSIM on test set.

关键词： Context modeling Solid modeling Image coding Entropy Training Transforms Image resolution

3-D context entropy model for improved practical image compression

学校读者我要写书评

暂无评论

arXiv 2020年

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

关键词： Image compression

Learned video compression with feature-level residuals

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Feng, Runsen Wu, Yaojun Guo, Zongyu Zhang, Zhizheng Jin, Xin Chen, Zhibo CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China

In this paper, we present an end-to-end video compression network for P-frame challenge on CLIC. We focus on deep neural network (DNN) based video compression, and improve the current frameworks from three aspects. First, we notice that pixel space residuals is sensitive to the prediction errors of optical flow based motion compensation. To suppress the relative influence, we propose to compress the residuals of image feature rather than the residuals of image pixels. Furthermore, we combine the advantages of both pixel-level and feature-level residual compression methods by model ensembling. Finally, we propose a step-by-step training strategy to improve the training efficiency of the whole framework. Experiment results indicate that our proposed method achieves 0.9968 MS-SSIM on CLIC validation set and 0.9967 MS-SSIM on test set. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep neural networks

Multi-scale grouped dense network for VVC intra coding

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Li, Xin 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

Versatile Video Coding (H.266/VVC) standard achieves better image quality when keeping the same bits than any other conventional image codec, such as BPG, JPEG, and etc. However, it is still attractive and challenging to improve the image quality with high compression ratio on the basis of traditional coding techniques. In this paper, we design the multi-scale grouped dense network (MSGDN) to further reduce the compression artifacts by combining the multi-scale and grouped dense block, which are integrated as the post-process network of VVC intra coding. Besides, to improve the subjective quality of compressed image, we also present a generative adversarial network (MSGDN-GAN) by utilizing our MSGDN as generator. Across the extensive experiments on validation set, our MSGDN trained by MSE losses yields the PSNR of 32.622 on average with teams"IMC" and"haha" at the bit-rate of 0.15 in Low-rate track. Moreover, our MSGDN-GAN could achieve the better subjective performance. Copyright © 2020, The Authors. All rights reserved.

关键词： Image quality

Learned Video Compression with Feature-level Residuals

学校读者我要写书评

暂无评论

Learned Video Compression with Feature-level Residuals

IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

作者： Runsen Feng Yaojun Wu 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

ISBN: (数字)9781728193601

ISBN: (纸本)9781728193618

关键词： Image coding Training Optical imaging Adaptive optics Motion compensation Optical distortion Decoding