检索结果-内蒙古大学图书馆

EfficientFCN: Holistically-guided decoding 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 Zhang, Jiawei Ren, Jimmy S. Li, Hongsheng CUHK-SenseTime Joint Laboratory Chinese University of Hong Kong Hong Kong Shenzhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China SenseTime Research China

Both performance and efficiency are important to semantic segmentation. State-of-the-art semantic segmentation algorithms are mostly based on dilated Fully Convolutional Networks (dilatedFCN), which adopt dilated convolutions in the backbone networks to extract high-resolution feature maps for achieving high-performance segmentation performance. However, due to many convolution operations are conducted on the high-resolution feature maps, such dilatedFCN-based methods result in large computational complexity and memory consumption. To balance the performance and efficiency, there also exist encoder-decoder structures that gradually recover the spatial information by combining multi-level feature maps from the encoder. However, the performances of existing encoder-decoder methods are far from comparable with the dilatedFCN-based methods. In this paper, we propose the EfficientFCN, whose backbone is a common ImageNet pretrained network without any dilated convolution. A holistically-guided decoder is introduced to obtain the high-resolution semantic-rich feature maps via the multi-scale features from the encoder. The decoding task is converted to novel codebook generation and codeword assembly task, which takes advantages of the high-level and low-level features from the encoder. Such a framework achieves comparable or even better performance than state-of-the-art methods with only 1/3 of the computational cost. Extensive experiments on PASCAL Context, PASCAL VOC, ADE20K validate the effectiveness of the proposed EfficientFCN. Copyright © 2020, The Authors. All rights reserved.

关键词： Convolution

OSRT: Omnidirectional Image Super-Resolution with Distortion-aware Transformer

学校读者我要写书评

暂无评论

OSRT: Omnidirectional Image Super-Resolution with Distortion...

Conference on computer vision and Pattern Recognition (CVPR)

作者： Fanghua Yu Xintao Wang Mingdeng Cao Gen Li Ying Shan Chao Dong ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences ARC Tencent PCG The University of Tokyo Platform Technologies Tencent Online Video Shanghai Artificial Intelligence Laboratory

Omnidirectional images (ODIs) have obtained lots of research interest for immersive experiences. Although ODIs require extremely high resolution to capture details of the entire scene, the resolutions of most ODIs are insufficient. Previous methods attempt to solve this issue by image super-resolution (SR) on equirectangular projection (ERP) images. However, they omit geometric properties of ERP in the degradation process, and their models can hardly generalize to real ERP images. In this paper, we propose Fisheye downsampling, which mimics the real-world imaging process and synthesizes more realistic low-resolution samples. Then we design a distortion-aware Transformer (OSRT) to modulate ERP distortions continuously and self-adaptively. Without a cumbersome process, OSRT outperforms previous methods by about 0.2dB on PSNR. Moreover, we propose a convenient data augmentation strategy, which synthesizes pseudo ERP images from plain images. This simple strategy can alleviate the over-fitting problem of large networks and significantly boost the performance of ODISR. Extensive experiments have demonstrated the state-of-the-art performance of our OSRT.

关键词：

GRATIS: Deep Learning Graph Representation with Task-specific Topology and Multi-dimensional Edge Features

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Song, Siyang Song, Yuxin Luo, Cheng Song, Zhiyuan Kuzucu, Selim Jia, Xi Guo, Zhijiang Xie, Weicheng Shen, Linlin Gunes, Hatice The Department of Computer Science and Technology University of Cambridge CambridgeCB3 0FT United Kingdom Baidu Inc Beijing100193 China Computer Vision Institute School of Computer Science & Software Engineering Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China Department of Computer Engineering Middle East Technical University Ankara Turkey School of Computer Science University of Birmingham Birmingham United Kingdom

Graph is powerful for representing various types of real-world data. The topology (edges’ presence) and edges’ features of a graph decides the message passing mechanism among vertices within the graph. While most existing approaches only manually define a single-value edge to describe the connectivity or strength of association between a pair of vertices, task-specific and crucial relationship cues may be disregarded by such manually defined topology and single-value edge features. In this paper, we propose the first general graph representation learning framework (called GRATIS) which can generate a strong graph representation with a task-specific topology and task-specific multi-dimensional edge features from any arbitrary input (i.e., graph or non-graph data). To learn each edge’s presence and multi-dimensional feature, our framework takes both of the corresponding vertices pair and their global contextual information into consideration, enabling the generated graph representation to have a globally optimal message passing mechanism for different down-stream tasks. The principled investigation results achieved for various graph analysis tasks (e.g., graph classification, vertex classification, and link prediction) on 11 graph and non-graph datasets show that our GRATIS can not only largely enhance pre-defined graphs but also learns a strong graph representation for non-graph data, with clear performance improvements on all tasks. In particular, the learned topology and multi-dimensional edge features provide complementary task-related cues for graph analysis tasks. Our framework is effective, robust and flexible, and is a plug-and-play module that can be combined with different backbones and Graph Neural Networks (GNNs) to generate a task-specific graph representation from various graph and non-graph data. Our code is made publicly available at https://***/SSYSteve/Learning-Graph-Representation-with-Task-specific-Topology-and-Multi-dimensional-Edge-Feature

关键词： Graph neural networks

A unified leader-follower scheme for mobile robots with uncalibrated on-board camera

学校读者我要写书评

暂无评论

A unified leader-follower scheme for mobile robots with unca...

2017 IEEE International Conference on robotics and Automation, ICRA 2017

作者： Guo, Dejun Wang, Hesheng Chen, Weidong Liu, Ming Xia, Zeyang Leang, Kam K. Lab University of Utah Robotics Center Salt Lake CityUT84112 United States Department of Automation Shanghai Jiao Tong University Shanghai200240 China Department of Electronics and Computer Engineering Hong Kong University of Science and Technology Hong Kong Hong Kong Institute of Biomedical and Health Engineering Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China

ISBN: (纸本)9781509046331

This paper studies the problem of image-based leader-follower formation control for mobile robots, where the controller is designed independently of the leader's motion. An adaptive control scheme, which is suitable for both omnidirectional and perspective cameras, is proposed. The proposed approach avoids the need for accurate calibration of the extrinsic parameters of the omnidirectional camera as well as the intrinsic and extrinsic parameters of perspective camera. Additionally, the coefficients of the plane where the feature point moves relative to the camera frame can be uncertain. These uncertain constant parameters are estimated using an adaptive estimator. Uniform Semi-global Practical Asymptotic Stability (USPAS) of the system is shown using the Lyapunov approach. Experimental results are presented to demonstrate the effectiveness of the proposed control scheme. © 2017 IEEE.

关键词： Mobile robots

CA-Edit: Causality-Aware Condition Adapter for High-Fidelity Local Facial Attribute Editing

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xian, Xiaole He, Xilin Niu, Zenghao Zhang, Junliang Xie, Weicheng Song, Siyang Yu, Zitong Shen, Linlin Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Guangdong Key Laboratory of Intelligent Information Processing China University of Exeter United Kingdom Great Bay University China

For efficient and high-fidelity local facial attribute editing, most existing editing methods either require additional finetuning for different editing effects or tend to affect beyond the editing regions. Alternatively, inpainting methods can edit the target image region while preserving external areas. However, current inpainting methods still suffer from the generation misalignment with facial attributes description and the loss of facial skin details. To address these challenges, (i) a novel data utilization strategy is introduced to construct datasets consisting of attribute-text-image triples from a data-driven perspective, (ii) a Causality-Aware Condition Adapter is proposed to enhance the contextual causality modeling of specific details, which encodes the skin details from the original image while preventing conflicts between these cues and textual conditions. In addition, a Skin Transition Frequency Guidance technique is introduced for the local modeling of contextual causality via sampling guidance driven by low-frequency alignment. Extensive quantitative and qualitative experiments demonstrate the effectiveness of our method in boosting both fidelity and editability for localized attribute editing. The code is available at https://***/connorxian/CA-Edit. © 2024, CC BY.

关键词：

Federated Distributed Deep Reinforcement Learning for Recommendation-enabled Edge Caching

学校读者我要写书评

暂无评论

Federated Distributed Deep Reinforcement Learning for Recomm...

IEEE Conference on computer Communications Workshops, INFOCOM Wksps

作者： Hao Wang Huan Zhou Mingze Lit Liang Zhao 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 School of Computer Science Northwestern Polytechnical University Xi'an China College of Computer Science and Software Engineering Shenzhen University Shenzhen China

ISBN: (数字)9798350384475

ISBN: (纸本)9798350384482

This paper investigates a content recommendation-based edge caching method in multi-tier edge-cloud networks while considering content delivery and cache replacement decisions as well as bandwidth allocation strategies. First, we formu-late the optimization problem with the goal of minimizing long-term content delivery delay. Second, we model the optimization problem as a Partially Observable Markov Decision Process, and propose a Federated Distributed Deep Deterministic Policy Gradient-based method (FD3PG) to solve the corresponding problem. In conclusion, simulation results demonstrate that the proposed FD3PG achieves not only a much lower content delivery delay but also a higher cache hit rate compared with other baselines in various scenarios.

关键词： Simulation Markov decision processes Conferences Channel allocation Deep reinforcement learning Delays Optimization

TD3-Based Collaborative Computation Offloading and Charging Scheduling in Multi-UAV-Assisted MEC Networks

学校读者我要写书评

暂无评论

TD3-Based Collaborative Computation Offloading and Charging ...

IEEE Conference on Wireless Communications and Networking

作者： Liang Zhao Yujun Yao Huan Zhou Hao Wang 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 School of Computer Science Northwestern Polytechnical University Xi'an China College of Computer Science and Software Engineering Shenzhen University Shenzhen China

ISBN: (数字)9798350303582

ISBN: (纸本)9798350303599

Computation offloading, resource allocation, and endurance issues in unmanned aerial vehicle (UAV)-aided mobile edge computing (MEC) networks have always been a research focus. UAV-aided MEC allows mobile users (MUs)' tasks to be offloaded to drones for processing in special scenarios, such as natural disasters or military attacks. However, as the number and size of offloaded tasks increase, a single UAV is difficult to meet all computational demands, result in the decline of QoS. To address this issue, this paper presents a collaborative computation offloading scheme where multiple UAVs can cooperate to handle massive tasks. Firstly, considering that battery-limited UAVs cannot complete all tasks and sustain flight without charging, we incorporate charging stations (CS) into multi-UAV-assisted MEC networks. Subsequently, we design a price-based incentive mechanism to maximize the total revenue obtained from UAVs' collaborative computation. Then, we formulate the joint optimization problem of computation offloading, resource allocation and charging scheduling as a Markov Decision Process (MDP), and propose a Twin Delayed Deep Deterministic policy gradient (TD3) algorithm to find optimal strategies. Finally, extensive simulations demonstrate that the proposed TD3 algorithm outperforms other benchmark methods, achieving the highest overall system utility under different scenarios.

关键词： Processor scheduling Computational modeling Inductive charging Collaboration Charging stations Scheduling Resource management

Exploring Intra- and Inter-Video Relation for Surgical Semantic Scene Segmentation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Jin, Yueming Yu, Yang Chen, Cheng Zhao, Zixu Heng, Pheng-Ann Stoyanov, Danail The Department of Computer Science University College London United Kingdom The Department of Computer Science and Engineering The Chinese University of Hong Kong HKSAR China Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China

Automatic surgical scene segmentation is fundamental for facilitating cognitive intelligence in the modern operating theatre. Previous works rely on conventional aggregation modules (e.g., dilated convolution, convolutional LSTM), which only make use of the local context. In this paper, we propose a novel framework STswinCL that explores the complementary intra- and inter-video relations to boost segmentation performance, by progressively capturing the global context. We firstly develop a hierarchy Transformer to capture intra-video relation that includes richer spatial and temporal cues from neighbor pixels and previous frames. A joint space-time window shift scheme is proposed to efficiently aggregate these two cues into each pixel embedding. Then, we explore inter-video relation via pixel-to-pixel contrastive learning, which well structures the global embedding space. A multi-source contrast training objective is developed to group the pixel embeddings across videos with the ground-truth guidance, which is crucial for learning the global property of the whole data. We extensively validate our approach on two public surgical video benchmarks, including EndoVis18 Challenge and CaDIS dataset. Experimental results demonstrate the promising performance of our method, which consistently exceeds previous state-of-the-art approaches. Code is available at https://***/YuemingJin/STswinCL. Copyright © 2022, The Authors. All rights reserved.

关键词： Pixels

Aesthetically Relevant Image Captioning

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhong, Zhipeng Zhou, Fei Qiu, Guoping College of Electronics and Information Engineering Shenzhen University China Peng Cheng National Laboratory Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen China Shenzhen Institute for Artificial Intelligence and Robotics for Society China Guangdong-Hong Kong Joint Laboratory for Big Data Imaging and Communication Shenzhen China School of Computer Science The University of Nottingham United Kingdom

Image aesthetic quality assessment (AQA) aims to assign numerical aesthetic ratings to images whilst image aesthetic captioning (IAC) aims to generate textual descriptions of the aesthetic aspects of images. In this paper, we study image AQA and IAC together and present a new IAC method termed Aesthetically Relevant Image Captioning (ARIC). Based on the observation that most textual comments of an image are about objects and their interactions rather than aspects of aesthetics, we first introduce the concept of Aesthetic Relevance Score (ARS) of a sentence and have developed a model to automatically label a sentence with its ARS. We then use the ARS to design the ARIC model which includes an ARS weighted IAC loss function and an ARS based diverse aesthetic caption selector (DACS). We present extensive experimental results to show the soundness of the ARS concept and the effectiveness of the ARIC model by demonstrating that texts with higher ARS’s can predict the aesthetic ratings more accurately and that the new ARIC model can generate more accurate, aesthetically more relevant and more diverse image captions. Furthermore, a large new research database containing 510K images with over 5 million comments and 350K aesthetic scores, and code for implementing ARIC are available at https://***/PengZai/ARIC. © 2022, CC BY-NC-ND.

关键词：