检索结果-内蒙古大学图书馆

Learning to predict context-adaptive convolution for semantic segmentation

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Liu, Jianbo He, Junjun Ren, Jimmy S. Qiao, Yu Li, Hongsheng CUHK-SenseTime Joint Laboratory Chinese University of Hong Kong Shenzhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences SenseTime Research

Long-range contextual information is essential for achieving high-performance semantic segmentation. Previous feature re-weighting methods [34] demonstrate that using global context for re-weighting feature channels can effectively improve the accuracy of semantic segmentation. However, the globally-sharing feature re-weighting vector might not be optimal for regions of different classes in the input image. In this paper, we propose a Context-adaptive Convolution Network (CaC-Net) to predict a spatially-varying feature weighting vector for each spatial location of the semantic feature maps. In CaC-Net, a set of context-adaptive convolution kernels are predicted from the global contextual information in a parameter-efficient manner. When used for convolution with the semantic feature maps, the predicted convolutional kernels can generate the spatially-varying feature weighting factors capturing both global and local contextual information. Comprehensive experimental results show that our CaC-Net achieves superior segmentation performance on three public datasets, PASCAL Context, PASCAL VOC 2012 and ADE20K. Copyright © 2020, The Authors. All rights reserved.

关键词： Convolution

Learning dynamical human-joint affinity for 3D pose estimation in videos

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhang, Junhao Wang, Yali Zhou, Zhipeng Luan, Tianyu Wang, Zhe Qiao, Yu ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences University of California Irvine United States Shanghai AI Laboratory Shanghai China

Graph Convolution Network (GCN) has been successfully used for 3D human pose estimation in videos. However, it is often built on the fixed human-joint affinity, according to human skeleton. This may reduce adaptation capacity of GCN to tackle complex spatio-temporal pose variations in videos. To alleviate this problem, we propose a novel Dynamical Graph Network (DG-Net), which can dynamically identify human-joint affinity, and estimate 3D pose by adaptively learning spatial/temporal joint relations from videos. Different from traditional graph convolution, we introduce Dynamical Spatial/Temporal Graph convolution (DSG/DTG) to discover spatial/temporal human-joint affinity for each video exemplar, depending on spatial distance/temporal movement similarity between human joints in this video. Hence, they can effectively understand which joints are spatially closer and/or have consistent motion, for reducing depth ambiguity and/or motion uncertainty when lifting 2D pose to 3D pose. We conduct extensive experiments on three popular benchmarks, e.g., Human3.6M, HumanEva-I, and MPI-INF-3DHP, where DG-Net outperforms a number of recent SOTA approaches with fewer input frames and model size. Copyright © 2021, The Authors. All rights reserved.

关键词： Convolution

Boundary and entropy-driven adversarial learning for fundus image segmentation

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Wang, Shujun Yu, Lequan Li, Kang Yang, Xin Fu, Chi-Wing Heng, Pheng-Ann Department of Computer Science and Engineering Chinese University of Hong Kong Hong Kong Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China

Accurate segmentation of the optic disc (OD) and cup (OC) in fundus images from different datasets is critical for glaucoma disease screening. The cross-domain discrepancy (domain shift) hinders the generalization of deep neural networks to work on different domain datasets. In this work, we present an unsupervised domain adaptation framework, called Boundary and Entropy-driven Adversarial Learning (BEAL), to improve the OD and OC segmentation performance, especially on the ambiguous boundary regions. In particular, our proposed BEAL frame-work utilizes the adversarial learning to encourage the boundary prediction and mask probability entropy map (uncertainty map) of the target domain to be similar to the source ones, generating more accurate boundaries and suppressing the high uncertainty predictions of OD and OC segmentation. We evaluate the proposed BEAL framework on two public retinal fundus image datasets (Drishti-GS and RIM-ONE-r3), and the experiment results demonstrate that our method outperforms the state-of-the-art unsupervised domain adaptation methods. Our code is available at https://***/EmmaW8/BEAL. Copyright © 2019, The Authors. All rights reserved.

关键词： Entropy

DegAE: A New Pretraining Paradigm for Low-Level vision

学校读者我要写书评

暂无评论

DegAE: A New Pretraining Paradigm for Low-Level Vision

Conference on computer vision and Pattern Recognition (CVPR)

作者： Yihao Liu Jingwen He Jinjin Gu Xiangtao Kong Yu Qiao Chao Dong Shanghai Artificial Intelligence Laboratory ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences University of Chinese Academy of Sciences The University of Sydney

Self-supervised pretraining has achieved remarkable success in high-level vision, but its application in low-level vision remains ambiguous and not well-established. What is the primitive intention of pretraining? What is the core problem of pretraining in low-level vision? In this paper, we aim to answer these essential questions and establish a new pretraining scheme for low-level vision. Specifically, we examine previous pretraining methods in both high-level and low-level vision, and categorize current low-level vision tasks into two groups based on the difficulty of data acqui-sition: low-cost and high-cost tasks. Existing literature has mainly focused on pretraining for low-cost tasks, where the observed performance improvement is often limited. However, we argue that pretraining is more significant for high-cost tasks, where data acquisition is more challenging. To learn a general low-level vision representation that can improve the performance of various tasks, we propose a new pretraining paradigm called degradation autoencoder (De-gAE). DegAE follows the philosophy of designing pretext task for self-supervised pretraining and is elaborately tai-lored to low-level vision. With DegAE pretraining, SwinIR achieves a 6.88dB performance gain on image dehaze task, while Uformer obtains 3.22dB and 0.54dB improvement on dehaze and derain tasks, respectively.

关键词：

Dynamic hand gesture early recognition based on Hidden Semi-Markov Models

学校读者我要写书评

暂无评论

Dynamic hand gesture early recognition based on Hidden Semi-...

IEEE International Conference on robotics and Biomimetics

作者： Qianqian Wang Yuanrong Xu Yen-Lun Chen Yong Wang Xinyu Wu University of Science and Technology of China Shenzhen Key Lab for Computer Vision and Pattern Recognition Chinese Academy of Sciences Dept. Mechanical and Automation Engineering The Chinese University of Hong Kong. Guangdong Provincial Key Laboratory of Robotics and Intelligent System Chinese Academy of Sciences

ISBN: (纸本)9781479973989

Real-time performance can be greatly improved, if the early recognition is implemented. In this paper, a dynamic hand gesture early recognition system is proposed. The system can recognize the gesture before it is completed. Our method is based on the Hidden Semi-Markov Models. Three-dimensional information of the gesture trajectory collected by leapmotion is the main data we used. Experiments on the dataset which we established demonstrate the effectiveness of our method.

关键词： Hidden Markov models Gesture recognition Training Conferences Trajectory Arrays

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