检索结果-内蒙古大学图书馆

computer vision and Image Understanding

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Tang, Wenming Gong, Yuanhao Qiu, Guoping College of Electronics and Information Engineering Shenzhen University Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China School of Computer Science The University of Nottingham United Kingdom

Graph neural networks (GNNs) are ideally suited for mesh denoising. However, existing solutions such as those based on graph convolutional networks (GCNs) are built for a fixed graph thus making them not naturally generalisable to unseen meshes. Furthermore, their graph Laplacian based global node embedding algorithms can cause excessive smoothing while achieving feature preserving mesh denoising requires a GNN to posses local processing capability. This paper presents a mesh denoising method via a new Dense lOcal Graph neural NETwork (DOGNET). DOGNET implements a local node embedding algorithm that generates node embeddings through aggregating information from a node’s connected local neighbours which automatically make DOGNET inductive as well as effective for feature preserving mesh denoising. We present extensive experimental results to demonstrate quantitatively and qualitatively that DOGNET is superior to SOTA meshing denoising techniques. © 2022, The Authors. All rights reserved.

关键词： Graph neural networks

Context-transformer: Tackling object confusion for few-shot detection

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Yang, Ze Wang, Yali Chen, Xianyu Liu, Jianzhuang Qiao, Yu ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab. Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Huawei Noah’s Ark Lab. SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society

Few-shot object detection is a challenging but realistic scenario, where only a few annotated training images are available for training detectors. A popular approach to handle this problem is transfer learning, i.e., fine-tuning a detector pretrained on a source-domain benchmark. However, such transferred detector often fails to recognize new objects in the target domain, due to low data diversity of training samples. To tackle this problem, we propose a novel Context-Transformer within a concise deep transfer framework. Specifically, Context-Transformer can effectively leverage source-domain object knowledge as guidance, and automatically exploit contexts from only a few training images in the target domain. Subsequently, it can adaptively integrate these relational clues to enhance the discriminative power of detector, in order to reduce object confusion in few-shot scenarios. Moreover, Context-Transformer is flexibly embedded in the popular SSD-style detectors, which makes it a plug-and-play module for end-to-end few-shot learning. Finally, we evaluate Context-Transformer on the challenging settings of few-shot detection and incremental few-shot detection. The experimental results show that, our framework outperforms the recent state-of-the-art approaches. The codes are available at https://***/Ze-Yang/ContextTransformer. Copyright © 2020, The Authors. All rights reserved.

关键词： Object detection

Incentive-driven Federated Learning in Mobile Edge Networks

学校读者我要写书评

暂无评论

Incentive-driven Federated Learning in Mobile Edge Networks

International Conference on Distributed Computing Systems Workshop

作者： Yanlang Zheng Huan Zhou Liang Zhao Shouzhi Xu Victor C. M. Leung Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering College of Computer and Information Technology China Three Gorges University Yichang China College of Computer Science and Software Engineering Shenzhen University Shenzhen China

Federated Learning (FL) is proposed as a privacy-preserving distributed learning methodology that can better protect the privacy and reduce communication costs. To stimulate sufficient User Equipments (UEs) to participate in FL, proper incentives need to be designed for FL. Existing incentive mechanisms do not jointly consider UE selection and local learning accuracy optimization to reduce the training expenditure. This paper designs a reverse auction-based incentive mechanism for FL to minimize the training expenditure of Base Station (BS). To this end, we first propose a Greedy Winner Determination (GWD) algorithm to select UEs with the minimum bidding prices. Then, we incorporate the Particle Swarm Optimization (PSO)-based local learning accuracy optimization into UE selection to further reduce the training expenditure of BS. In addition, we design a Vickrey Clarke Groves (VCG)-based payment rule to determine the payment to each participating UE. The simulation experiments show that our proposed PSO with Winner Determination (PSOWD) algorithm is superior to other existing methods in different scenarios.

关键词：

SATO: Stable Text-to-Motion Framework 24

学校读者我要写书评

暂无评论

SATO: Stable Text-to-Motion Framework

32nd ACM International Conference on Multimedia, MM 2024

作者： Chen, Wenshuo Xiao, Hongru Zhang, Erhang Hu, Lijie Wang, Lei Liu, Mengyuan Chen, Chen Shandong University Qingdao China Tongji University Shanghai China King Abdullah University of Science and Technology Jeddah Saudi Arabia Australian National University Data61/CSIRO Canberra Australia State Key Laboratory of General Artificial Intelligence Peking University Shenzhen Graduate School Shenzhen China Center for Research in Computer Vision University of Central Florida Orlando United States

ISBN: (纸本)9798400706868

Is the Text to Motion model robust? Recent advancements in Text to Motion models primarily stem from more accurate predictions of specific actions. However, the text modality typically relies solely on pre-trained Contrastive Language-Image Pretraining (CLIP) models. Our research has uncovered a significant issue with the text-to-motion model: its predictions often exhibit inconsistent outputs, resulting in vastly different or even incorrect poses when presented with semantically similar or identical text inputs. In this paper, we undertake an analysis to elucidate the underlying causes of this instability, establishing a clear link between the unpredictability of model outputs and the erratic attention patterns of the text encoder module. Consequently, we introduce a formal framework aimed at addressing this issue, which we term the Sta ble Text-to-Motion Framework (SATO). SATO consists of three modules, each dedicated to stable attention, stable prediction, and maintaining a balance between accuracy and robustness trade-off. We present a methodology for constructing an SATO that satisfies the stability of attention and prediction. To verify the stability of the model, we introduced a new textual synonym perturbation dataset based on HumanML3D and KIT-ML. Results show that SATO is significantly more stable against synonyms and other slight perturbations while keeping its high accuracy performance. Codes and models are released at https://***/sato-team/Stable-Text-to-Motion-Framework. © 2024 ACM.

关键词： Semantics

MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Li, Wenhao Liu, Hong Tang, Hao Wang, Pichao Van Gool, Luc Key Laboratory of Machine Perception Shenzhen Graduate School Peking University China Computer Vision Lab. ETH Zurich Switzerland Alibaba Group China

Estimating 3D human poses from monocular videos is a challenging task due to depth ambiguity and self-occlusion. Most existing works attempt to solve both issues by exploiting spatial and temporal relationships. However, those works ignore the fact that it is an inverse problem where multiple feasible solutions (i.e., hypotheses) exist. To relieve this limitation, we propose a Multi-Hypothesis Transformer (MHFormer) that learns spatio-temporal representations of multiple plausible pose hypotheses. In order to effectively model multi-hypothesis dependencies and build strong relationships across hypothesis features, the task is decomposed into three stages: (i) Generate multiple initial hypothesis representations;(ii) Model self-hypothesis communication, merge multiple hypotheses into a single converged representation and then partition it into several diverged hypotheses;(iii) Learn cross-hypothesis communication and aggregate the multi-hypothesis features to synthesize the final 3D pose. Through the above processes, the final representation is enhanced and the synthesized pose is much more accurate. Extensive experiments show that MHFormer achieves state-of-the-art results on two challenging datasets: Human3.6M and MPI-INF-3DHP. Without bells and whistles, its performance surpasses the previous best result by a large margin of 3% on Human3.6M. Code and models are available at https://***/Vegetebird/MHFormer. Copyright © 2021, The Authors. All rights reserved.

关键词： Inverse problems

Neuron segmentation using 3D wavelet integrated encoder-decoder network

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Li, Qiufu Shen, Linlin Computer Vision Institute College of Computer Science and Software Engineering Shen zhen University Shenzhen518060 China AI Research Center for Medical Image Analysis and Diagnosis Shenzhen University Shenzhen518060 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China Marshall Laboratory of Biomedical Engineering Shenzhen University Shenzhen518060 China

Motivation: 3D neuron segmentation is a key step for the neuron digital reconstruction, which is essential for exploring brain circuits and understanding brain functions. However, the fine line-shaped nerve fibers of neuron could spread in a large region, which brings great computational cost to the neuron segmentation. Meanwhile, the strong noises and disconnected nerve fibers bring great challenges to the task. Results: In this paper, we propose a 3D wavelet and deep learning based 3D neuron segmentation method. The neuronal image is first partitioned into neuronal cubes to simplify the segmentation task. Then, we design 3D WaveUNet, the first 3D wavelet integrated encoder-decoder network, to segment the nerve fibers in the cubes;the wavelets could assist the deep networks in suppressing data noises and connecting the broken fibers. We also produce a Neuronal Cube Dataset (NeuCuDa) using the biggest available annotated neuronal image dataset, BigNeuron, to train 3D WaveUNet. Finally, the nerve fibers segmented in cubes are assembled to generate the complete neuron, which is digitally reconstructed using an available automatic tracing algorithm. The experimental results show that our neuron segmentation method could completely extract the target neuron in noisy neuronal images. The integrated 3D wavelets can efficiently improve the performance of 3D neuron segmentation and reconstruction. © 2021, CC BY.

关键词： Neurons

RDA: An Accelerated Collision Free Motion Planner for Autonomous Navigation in Cluttered Environments

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Han, Ruihua Wang, Shuai Wang, Shuaijun Zhang, Zeqing Zhang, Qianru Eldar, Yonina C. Hao, Qi Pan, Jia The Department of Computer Science and Engineering Southern University of Science and Technology Guangdong Shenzhen China The Department of Computer Science The University of Hong Kong Hong Kong Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Shenzhen China The Department of Computer Science and Engineering Harbin Institute of Technology Guangdong Shenzhen China The Weizmann Institute of Science Rehovot Israel The Department of Computer Science and Engineering The Shenzhen Key Laboratory of Robotics and Computer Vision The Sifakis Research Institute for Trustworthy Autonomous Systems Southern University of Science and Technology Guangdong Shenzhen China

Autonomous motion planning is challenging in multi-obstacle environments due to nonconvex collision avoidance constraints. Directly applying numerical solvers to these nonconvex formulations fails to exploit the constraint structures, resulting in excessive computation time. In this paper, we present an accelerated collision-free motion planner, namely regularized dual alternating direction method of multipliers (RDADMM or RDA for short), for the model predictive control (MPC) based motion planning problem. The proposed RDA addresses nonconvex motion planning via solving a smooth biconvex reformulation via duality and allows the collision avoidance constraints to be computed in parallel for each obstacle to reduce computation time significantly. We validate the performance of the RDA planner through path-tracking experiments with car-like robots in both simulation and real-world settings. Experimental results show that the proposed method generates smooth collision-free trajectories with less computation time compared with other benchmarks and performs robustly in cluttered environments. The source code is available at https://***/hanruihua/ RDA_planner. Copyright © 2022, The Authors. All rights reserved.

关键词： Motion planning

VHS to HDTV video translation using multi-task adversarial learning

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Luo, Hongming Liao, Guangsen Hou, Xianxu Liu, Bozhi Zhou, Fei Qiu, Guoping College of Electronics and Information Engineering Shenzhen University Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen China Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China School of Computer Science University of Nottingham Nottingham United Kingdom

There are large amount of valuable video archives in Video Home System (VHS) format. However, due to the analog nature, their quality is often poor. Compared to High-definition television (HDTV), VHS video not only has a dull color appearance but also has a lower resolution and often appears blurry. In this paper, we focus on the problem of translating VHS video to HDTV video and have developed a solution based on a novel unsupervised multi-task adversarial learning model. Inspired by the success of generative adversarial network (GAN) and CycleGAN, we employ cycle consistency loss, adversarial loss and perceptual loss together to learn a translation model. An important innovation of our work is the incorporation of super-resolution model and color transfer model that can solve unsupervised multi-task problem. To our knowledge, this is the first work that dedicated to the study of the relation between VHS and HDTV and the first computational solution to translate VHS to HDTV. We present experimental results to demonstrate the effectiveness of our solution qualitatively and quantitatively. Copyright © 2021, The Authors. All rights reserved.

关键词： Generative adversarial networks

FeCAM: exploiting the heterogeneity of class distributions in exemplar-free continual learning 23

学校读者我要写书评

暂无评论

FeCAM: exploiting the heterogeneity of class distributions i...

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Dipam Goswami Yuyang Liu Bartłomiej Twardowski Joost van de Weijer Department of Computer Science Universitat Autònoma de Barcelona and Computer Vision Center Barcelona University of Chinese Academy of Sciences and State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences and Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Department of Computer Science Universitat Autònoma de Barcelona and Computer Vision Center Barcelona and IDEAS-NCBR

Exemplar-free class-incremental learning (CIL) poses several challenges since it prohibits the rehearsal of data from previous tasks and thus suffers from catastrophic forgetting. Recent approaches to incrementally learning the classifier by freezing the feature extractor after the first task have gained much attention. In this paper, we explore prototypical networks for CIL, which generate new class prototypes using the frozen feature extractor and classify the features based on the Euclidean distance to the prototypes. In an analysis of the feature distributions of classes, we show that classification based on Euclidean metrics is successful for jointly trained features. However, when learning from non-stationary data, we observe that the Euclidean metric is suboptimal and that feature distributions are heterogeneous. To address this challenge, we revisit the anisotropic Mahalanobis distance for CIL. In addition, we empirically show that modeling the feature covariance relations is better than previous attempts at sampling features from normal distributions and training a linear classifier. Unlike existing methods, our approach generalizes to both many- and few-shot CIL settings, as well as to domain-incremental settings. Interestingly, without updating the backbone network, our method obtains state-of-the-art results on several standard continual learning benchmarks. Code is available at https://***/dipamgoswami/FeCAM.

关键词：