检索结果-内蒙古大学图书馆

AniGAN: Style-guided generative adversarial networks for unsupervised anime face generation

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Li, Bing Zhu, Yuanlue Wang, Yitong Lin, Chia-Wen Ghanem, Bernard Shen, Linlin Visual Computing Center KAUST Thuwal Saudi Arabia ByteDance Shenzhen China Department of Electrical Engineering National Tsing Hua University Hsinchu Taiwan Computer Science and Software Engineering Shenzhen University Shenzhen China

In this paper, we propose a novel framework to translate a portrait photo-face into an anime appearance. Our aim is to synthesize anime-faces which are style-consistent with a given reference anime-face. However, unlike typical translation tasks, such anime-face translation is challenging due to complex variations of appearances among anime-faces. Existing methods often fail to transfer the styles of reference anime-faces, or introduce noticeable artifacts/distortions in the local shapes of their generated faces. We propose AniGAN, a novel GAN-based translator that synthesizes high-quality anime-faces. Specifically, a new generator architecture is proposed to simultaneously transfer color/texture styles and transform local facial shapes into anime-like counterparts based on the style of a reference anime-face, while preserving the global structure of the source photo-face. We propose a double-branch discriminator to learn both domain-specific distributions and domain-shared distributions, helping generate visually pleasing anime-faces and effectively mitigate artifacts. Extensive experiments on selfie2anime and a new face2anime dataset qualitatively and quantitatively demonstrate the superiority of our method over state-of-the-art methods. The new dataset is available at https://***/bing-liai/AniGAN. Copyright © 2021, The Authors. All rights reserved.

关键词： Generative adversarial networks

Learning Semantic-Agnostic and Spatial-Aware Representation for Generalizable visual-Audio Navigation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, Hongcheng Wang, Yuxuan Zhong, Fangwei Wu, Mingdong Zhang, Jianwei Wang, Yizhou Dong, Hao School of Computer Science Peking University Beijing100871 China Academy for Advanced Interdisciplinary Studies Peking University Beijing100871 China School of Intelligence and Technology Peking University National Key Laboratory of General Artificial Intelligence BIGAI Beijing100871 China TAMS Department of Informatics Universität Hamburg Germany The Center on Frontiers of Computing Studies Institute for Artificial Intelligence Peking University Beijing100871 China The Nat’l Eng. Research Center of Visual Technology Beijing100871 China

visual-audio navigation (VAN) is attracting more and more attention from the robotic community due to its broad applications, e.g., household robots and rescue robots. In this task, an embodied agent must search for and navigate to the sound source with egocentric visual and audio observations. However, the existing methods are limited in two aspects: 1) poor generalization to unheard sound categories;2) sample inefficient in training. Focusing on these two problems, we propose a brain-inspired plug-and-play method to learn a semantic-agnostic and spatial-aware representation for generalizable visual-audio navigation. We meticulously design two auxiliary tasks for respectively accelerating learning representations with the above-desired characteristics. With these two auxiliary tasks, the agent learns a spatially-correlated representation of visual and audio inputs that can be applied to work on environments with novel sounds and maps. Experiment results on realistic 3D scenes (Replica and Matterport3D) demonstrate that our method achieves better generalization performance when zero-shot transferred to scenes with unseen maps and unheard sound categories. Copyright © 2023, The Authors. All rights reserved.

关键词： Reinforcement learning

Cross-domain Contrastive Learning for Unsupervised Domain Adaptation

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wang, Rui Wu, Zuxuan Weng, Zejia Chen, Jingjing Qi, Guo-Jun Jiang, Yu-Gang Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai Collaborative Innovation Center on Intelligent Visual Computing China Seattle Cloud Lab Futurewei Technologies BellevueWA98004 United States

Unsupervised domain adaptation (UDA) aims to transfer knowledge learned from a fully-labeled source domain to a different unlabeled target domain. Most existing UDA methods learn domain-invariant feature representations by minimizing feature distances across domains. In this work, we build upon contrastive self-supervised learning to align features so as to reduce the domain discrepancy between training and testing sets. Exploring the same set of categories shared by both domains, we introduce a simple yet effective framework CDCL, for domain alignment. In particular, given an anchor image from one domain, we minimize its distances to cross-domain samples from the same class relative to those from different categories. Since target labels are unavailable, we use a clustering-based approach with carefully initialized centers to produce pseudo labels. In addition, we demonstrate that CDCL is a general framework and can be adapted to the data-free setting, where the source data are unavailable during training, with minimal modification. We conduct experiments on two widely used domain adaptation benchmarks, i.e., Office-31 and VisDA-2017, for image classification tasks, and demonstrate that CDCL achieves state-of-the-art performance on both datasets. Copyright © 2021, The Authors. All rights reserved.

关键词： Benchmarking

Challenges of 3D Surface Reconstruction in Capsule Endoscopy

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Rukundo, Olivier Norwegian Colour and Visual Computing Laboratory Department of Computer Science Norwegian University of Science and Technology Teknologiveien 22 Gjøvik2815 Norway Center for Clinical Research University Clinic of Dentistry Medical University of Vienna Sensengasse 2a Vienna1090 Austria

Essential for improving the accuracy and reliability of bowel cancer screening, three-dimensional (3D) surface reconstruction using capsule endoscopy (CE) images remains challenging due to CE hardware and software limitations. This report generally focuses on challenges associated with 3D visualization and specifically investigates the impact of the indeterminate selection of the angle of the line–of–sight on 3D surfaces. Furthermore, it demonstrates that impact through 3D surfaces viewed at the same azimuth angles and different elevation angles of the line–of–sight. The report concludes that 3D printing of reconstructed 3D surfaces can potentially overcome line–of–sight indeterminate selection and 2D screen visual restriction-related errors. © 2021, CC BY.

关键词： Image reconstruction

Vortex criteria can be objectivized by unsteadiness minimization

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Theisel, Holger Hadwiger, Markus Rautek, Peter Theußl, Thomas Günther, Tobias Department of Computer Science Otto-von-Guericke University of Magdeburg Magdeburg Germany Visual Computing Center King Abdullah University of Science and Technology Thuwal23955-6900 Saudi Arabia Visualization Core Lab King Abdullah University of Science and Technology Thuwal23955-6900 Saudi Arabia Department of Computer Science Friedrich-Alexander-University of Erlangen-Nuremberg Erlangen Germany

Reference frame optimization is a generic framework to calculate a spatially-varying observer field that views an unsteady fluid flow in a reference frame that is as-steady-as-possible. In this paper, we show that the optimized vector field is objective, i.e., it is independent of the initial Euclidean transformation of the observer. To check objectivity, the optimized velocity vectors and the coordinates in which they are defined must both be connected by an Euclidean transformation. In this paper we show that a recent publication [1] applied this definition incorrectly, falsely concluding that reference frame optimizations are not objective. Further, we prove the objectivity of the variational formulation of the reference frame optimization proposed in [1], and discuss how the variational formulation relates to recent local and global optimization approaches to unsteadiness minimization. © 2021, CC BY.

关键词： Global optimization

VideoLT: Large-scale long-tailed video recognition

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhang, Xing Wu, Zuxuan Weng, Zejia Fu, Huazhu Chen, Jingjing Jiang, Yu-Gang Davis, Larry Academy for Engineering and Technology Fudan University Shanghai Key Lab of Intel. Info. Processing School of Computer Science Fudan University Shanghai Collaborative Innovation Center on Intelligent Visual Computing Inception Institute of Artificial Intelligence University of Maryland

Label distributions in real-world are oftentimes long-tailed and imbalanced, resulting in biased models towards dominant labels. While long-tailed recognition has been extensively studied for image classification tasks, limited effort has been made for the video domain. In this paper, we introduce VideoLT, a large-scale long-tailed video recognition dataset, as a step toward real-world video recognition. VideoLT contains 256,218 untrimmed videos, annotated into 1,004 classes with a long-tailed distribution. Through extensive studies, we demonstrate that state-of-the-art methods used for long-tailed image recognition do not perform well in the video domain due to the additional temporal dimension in videos. This motivates us to propose FrameStack, a simple yet effective method for long-tailed video recognition. In particular, FrameStack performs sampling at the frame-level in order to balance class distributions, and the sampling ratio is dynamically determined using knowledge derived from the network during training. Experimental results demonstrate that FrameStack can improve classification performance without sacrificing the overall accuracy. Code and dataset are available at: https://***/17Skye17/VideoLT. Copyright © 2021, The Authors. All rights reserved.

关键词： Image recognition

VideoLT: Large-scale Long-tailed Video Recognition

学校读者我要写书评

暂无评论

VideoLT: Large-scale Long-tailed Video Recognition

International Conference on computer Vision (ICCV)

作者： Xing Zhang Zuxuan Wu Zejia Weng Huazhu Fu Jingjing Chen Yu-Gang Jiang Larry Davis Academy for Engineering and Technology Fudan University Shanghai Key Lab of Intel. Info. Processing School of Computer Science Fudan University Shanghai Collaborative Innovation Center on Intelligent Visual Computing Inception Institute of Artificial Intelligence University of Maryland

ISBN: (纸本)9781665428132

关键词： Training Knowledge engineering computer vision Adaptation models Image recognition Codes Computational modeling

A Non-Asymptotic Analysis for Stein Variational Gradient Descent

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Korba, Anna Arbel, Michael Salim, Adil Luise, Giulia Gretton, Arthur Gatsby Computational Neuroscience Unit University College London Visual Computing Center KAUST Computer Science Department University College London

We study the Stein Variational Gradient Descent (SVGD) algorithm, which optimises a set of particles to approximate a target probability distribution π ∝ e−V on Rd. In the population limit, SVGD performs gradient descent in the space of probability distributions on the KL divergence with respect to π, where the gradient is smoothed through a kernel integral operator. In this paper, we provide a novel finite time analysis for the SVGD algorithm. We obtain a descent lemma establishing that the algorithm decreases the objective at each iteration, and provably converges, with less restrictive assumptions on the step size than required in earlier analyses. We further provide a guarantee on the convergence rate in Kullback-Leibler divergence, assuming π satisfies a Stein log-Sobolev inequality as in (Duncan et al., 2019), which takes into account the geometry induced by the smoothed KL gradient. Copyright © 2020, The Authors. All rights reserved.

关键词： Gradient methods

The wasserstein proximal gradient algorithm 20

学校读者我要写书评

暂无评论

The wasserstein proximal gradient algorithm

Proceedings of the 34th International Conference on Neural Information Processing Systems

作者： Adil Salim Anna Korba Giulia Luise Visual Computing Center KAUST Gatsby Computational Neuroscience Unit University College London Computer Science Department University College London

ISBN: (纸本)9781713829546

Wasserstein gradient flows are continuous time dynamics that define curves of steepest descent to minimize an objective function over the space of probability measures (i.e., the Wasserstein space). This objective is typically a divergence w.r.t. a fixed target distribution. In recent years, these continuous time dynamics have been used to study the convergence of machine learning algorithms aiming at approximating a probability distribution. However, the discrete-time behavior of these algorithms might differ from the continuous time dynamics. Besides, although discretized gradient flows have been proposed in the literature, little is known about their minimization power. In this work, we propose a Forward Backward (FB) discretization scheme that can tackle the case where the objective function is the sum of a smooth and a nonsmooth geodesically convex terms. Using techniques from convex optimization and optimal transport, we analyze the FB scheme as a minimization algorithm on the Wasserstein space. More precisely, we show under mild assumptions that the FB scheme has convergence guarantees similar to the proximal gradient algorithm in Euclidean spaces.

关键词：