检索结果-内蒙古大学图书馆

Feature Enhanced Projection Network for Zero-shot Semantic Segmentation

学校读者我要写书评

暂无评论

Feature Enhanced Projection Network for Zero-shot Semantic S...

IEEE International Conference on Robotics and Automation (ICRA)

作者： Hongchao Lu Longwei Fang Matthieu Lin Zhidong Deng Tsinghua University Beijing China Computer Vision Group Intel China State Key Laboratory of Intelligent Technology and Systems THUAI BNRist Center for Intelligent Connected Vehicles and Transportation Tsinghua University Beijing China

In environmental perception of autonomous driving, zero-shot semantic segmentation that can make prediction of new categories without using any labeled training samples is considered as a challenging task. One key step in this task is to transfer knowledge across categories via auxiliary semantic word embeddings. In this paper, we propose a feature enhanced projection network (FEPNet) that takes full advantage of transferred knowledge to enrich semantic representations. In FEPNet, two projection layers are added to a segmentation network so as to map features into seen (S) and unseen (U) category spaces, respectively. During training, U-space features are transferred to S-space using similarity relations to enhance the representation of seen categories. In the inference stage, the representation of unseen categories is also strengthened by incorporating features transferred from S-space. Moreover, a novel strategy is proposed to effectively alleviate prediction bias by performing segmentation independently in separate areas that contain seen and unseen categories. We conduct extensive experiments on three benchmark datasets. The experimental results show that our FEPNet achieves new state-of-the-art results compared to existing approaches.

关键词： Training Knowledge engineering Visualization Automation Conferences Semantics Benchmark testing

Learning from large-scale noisy web data with ubiquitous reweighting for image classification

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Li, Jia Song, Yafei Zhu, Jianfeng Cheng, Lele Su, Ying Ye, Lin Yuan, Pengcheng Han, Shumin State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing100191 China Shenzhen Cyberspace Laboratory Shenzhen China National Engineering Laboratory for Video Technology School of Electronics Engineering and Computer Science Peking University Beijing100871 China Computer Vision Technology Department of Baidu Beijing100871 China

Many advances of deep learning techniques originate from the efforts of addressing the image classification task on large-scale datasets. However, the construction of such clean datasets is costly and time-consuming since the Internet is overwhelmed by noisy images with inadequate and inaccurate tags. In this paper, we propose a Ubiquitous Reweighting Network (URNet) that learns an image classification model from large-scale noisy data. By observing the web data, we find that there are five key challenges, i.e., imbalanced class sizes, high intra-classes diversity and inter-class similarity, imprecise instances, insufficient representative instances, and ambiguous class labels. To alleviate these challenges, we assume that every training instance has the potential to contribute positively by alleviating the data bias and noise via reweighting the influence of each instance according to different class sizes, large instance clusters, its confidence, small instance bags and the labels. In this manner, the influence of bias and noise in the web data can be gradually alleviated, leading to the steadily improving performance of URNet. Experimental results in the Webvision 2018 challenge with 16 million noisy training images from 5000 classes show that our approach outperforms state-of-the-art models and ranks the first place in the image classification task. [***] 3 Apr 2019. Copyright © 2018, The Authors. All rights reserved.

关键词： Image classification

Research on Image Matching Technology for the Spherical Stereo vision

学校读者我要写书评

暂无评论

Research on Image Matching Technology for the Spherical Ster...

IEEE International Conference on Mechatronics and Automation

作者： Baofeng Zhang Na Liu Yingkui Jiao Yongchen Li Junchao Zhu Tianjin Key Laboratory for Control Theory and Applications in Complicated Systems Tianjin University of Technology 391 Binshui Xidao Xiqing District Tianjin 300384 China Key Laboratory of Computer Vision and System Ministry of Education of China School of Computer and Communication Engineering Tianjin University of Technology 391 Binshui Xidao Xiqing District Tianjin 300384 China

ISBN: (纸本)9781479970995

The technique of stereo matching is an important research goal of spherical stereo vision system, which is widely used in visual navigation, motion analysis and panoramic surveillance areas. Fisheye lens can get view images of large field, this paper uses two fisheye lens whose optical axis are perpendicular to construct spherical stereo vision system and does research in stereo matching of spherical stereo vision system. As the image that fish eye lens collected has lager distortion, this paper does stereo matching with the images the system collected without distortion correction using matching algorithm based on maximally stable extremal regions (MSER) and affine scale invariant feature transform (ASIFT) to reduce the correction error generated in the process. The experiment results show that the algorithm can be applied in stereo matching of fish eye image without distortion, and the results meets the need of 3D reconstruction.

关键词： Matching Spherical stereo vision Maximally Stable Extremal Regions (MSER) Affine Scale Invariant Feature Transform (ASIFT)

Learning a saliency evaluation metric using crowdsourced perceptual judgments

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Xia, Changqun Li, Jia Su, Jinming Borji, Ali State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China International Research Institute for Multidisciplinary Science Beihang University Beijing China Center for Research in Computer Vision Computer Science Department University of Central Florida OrlandoFL United States

In the area of human fixation prediction, dozens of computational saliency models are proposed to reveal certain saliency characteristics under different assumptions and definitions. As a result, saliency model benchmarking often requires several evaluation metrics to simultaneously assess saliency models from multiple perspectives. However, most computational metrics are not designed to directly measure the perceptual similarity of saliency maps so that the evaluation results may be sometimes inconsistent with the subjective impression. To address this problem, this paper first conducts extensive subjective tests to find out how the visual similarities between saliency maps are perceived by humans. Based on the crowdsourced data collected in these tests, we conclude several key factors in assessing saliency maps and quantize the performance of existing metrics. Inspired by these factors, we propose to learn a saliency evaluation metric based on a two-stream convolutional neural network using crowdsourced perceptual judgements. Specifically, the relative saliency score of each pair from the crowdsourced data is utilized to regularize the network during the training process. By capturing the key factors shared by various subjects in comparing saliency maps, the learned metric better aligns with human perception of saliency maps, making it a good complement to the existing metrics. Experimental results validate that the learned metric can be generalized to the comparisons of saliency maps from new images, new datasets, new models and synthetic data. Due to the effectiveness of the learned metric, it also can be used to facilitate the development of new models for fixation prediction. Copyright © 2018, The Authors. All rights reserved.

关键词： Crowdsourcing

A Lightweight Attention Network for Camouflaged Object Fixation Prediction

学校读者我要写书评

暂无评论

A Lightweight Attention Network for Camouflaged Object Fixat...

IEEE International Symposium on Industrial Electronics (ISIE)

作者： Qingbo Wu Guanxing Wu Shengyong Chen Key Laboratory of Computer Vision and Systems (Ministry of Education) Tianjin University of Technology Tianjin China Engineering Research Center of Learning-Based Intelligent System (Ministry of Education) Tianjin University of Technology Tianjin China School of Computer Science and Engineering Tianjin University of Technology Tianjin China

ISBN: (数字)9798350394085

ISBN: (纸本)9798350394092

This paper proposes a novel encoder-decoder architecture for camouflaged object fixation prediction (COFP), which builds on a large-kernel decomposition technique and depth-wise separable convolution embedded attention. Specifically, the encoder with the large-kernel decomposition adopts a Visual Attention Network (VAN) as the backbone to extract more accurate features, and the decoder predicts fixation maps from concealed objects using the attention module incorporating depth-wise separable convolution. Both designs aim to reduce the number of learnable parameters, making the model lighter and simultaneously maintaining the performance of COFP. In addition, we propose using the reverse Kullback-Leibler Divergence (KLDiv) as the loss function. Extensive experiments demonstrate that the proposed method performs well against SOTA approaches in quality and quantity.

关键词： Industrial electronics Visualization Accuracy Convolution Feature extraction Decoding

Advancing Virtual Reality Interaction: A Ring-Shaped Controller and Pose Tracking

学校读者我要写书评

暂无评论

Advancing Virtual Reality Interaction: A Ring-Shaped Control...

IEEE International Conference on Robotics and Automation (ICRA)

作者： Zhuqing Zhang Dongxuan Li Jiayao Ma Yijia He Pan Ji Rong Xiong Hongdong Li Yue Wang State Key Laboratory of Industrial Control Technology and Institute of Cyber-Systems and Control Zhejiang University Zhejiang China Tencent Holdings Tencent XR Vision Labs Shenzhen China College of Engineering and Computer Science Australian National University Canberra

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Ensuring robust tracking of controllers’ movement is critical for human-robot interaction in virtual reality (VR) scenarios. This paper proposes a robust tracking algorithm based on a novel wearable ring-shaped controller equipped with an inertial measurement unit (IMU) and a light-emitting diode (LED). This novel controller design allows users to free up their hands for more immersive experiences. To track the controller’s motion accurately and robustly, we resort to various forms of visual measurements, including 6 DoF and 5 DoF pose measurements from hand gesture detection, as well as 3 DoF position measurement and 2 DoF image measurement derived from the LED. We theoretically analyze the performances of these observation models and propose an optimal observation model combination scheme. Moreover, the necessity and rationale of online estimating system gravity are illustrated. The effectiveness of our tracking method is validated through extensive experiments.

关键词： Solid modeling Analytical models Visualization Measurement units Tracking Virtual reality Inertial navigation

Exploration of Class Center for Fine-Grained Visual Classification

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yao, Hang Miao, Qiguang Zhao, Peipei Li, Chaoneng Li, Xin Feng, Guanwen Liu, Ruyi The School of Computer Science and Technology Xidian University Shaanxi Xi’an710071 China Xi’an Key Laboratory of Big Data and Intelligent Vision Shaanxi Xi’an710071 China Key Laboratory of Collaborative Intelligence Systems Ministry of Education Xidian University Xi’an710071 China The School of Mechanical Engineering Yanshan University Qinhuangdao066004 China

Different from large-scale classification tasks, fine-grained visual classification is a challenging task due to two critical problems: 1) evident intra-class variances and subtle inter-class differences, and 2) overfitting owing to fewer training samples in datasets. Most existing methods extract key features to reduce intra-class variances, but pay no attention to subtle inter-class differences in fine-grained visual classification. To address this issue, we propose a loss function named exploration of class center, which consists of a multiple class-center constraint and a class-center label generation. This loss function fully utilizes the information of the class center from the perspective of features and labels. From the feature perspective, the multiple class-center constraint pulls samples closer to the target class center, and pushes samples away from the most similar nontarget class center. Thus, the constraint reduces intra-class variances and enlarges inter-class differences. From the label perspective, the class-center label generation utilizes class-center distributions to generate soft labels to alleviate overfitting. Our method can be easily integrated with existing fine-grained visual classification approaches as a loss function, to further boost excellent performance with only slight training costs. Extensive experiments are conducted to demonstrate consistent improvements achieved by our method on four widely-used fine-grained visual classification datasets. In particular, our method achieves state-of-the-art performance on the FGVC-Aircraft and CUB-200-2011 datasets. Copyright © 2024, The Authors. All rights reserved.

关键词： Large datasets

Edge-aware Feature Aggregation Network for Polyp Segmentation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhou, Tao Zhang, Yizhe Chen, Geng Zhou, Yi Wu, Ye Fan, Deng-Ping PCA Lab Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education The School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China School of Computer Science and Engineering NPU Xi’an China School of Computer Science and Engineering Southeast University Nanjing China Computer Vision Lab ETH Zürich Zürich Switzerland

Precise polyp segmentation is vital for the early diagnosis and prevention of colorectal cancer (CRC) in clinical practice. However, due to scale variation and blurry polyp boundaries, it is still a challenging task to achieve satisfactory segmentation performance with different scales and shapes. In this study, we present a novel Edge-aware Feature Aggregation Network (EFA-Net) for polyp segmentation, which can fully make use of cross-level and multi-scale features to enhance the performance of polyp segmentation. Specifically, we first present an Edge-aware Guidance Module (EGM) to combine the low-level features with the high-level features to learn an edge-enhanced feature, which is incorporated into each decoder unit using a layer-by-layer strategy. Besides, a Scale-aware Convolution Module (SCM) is proposed to learn scale-aware features by using dilated convolutions with different ratios, in order to effectively deal with scale variation. Further, a Cross-level Fusion Module (CFM) is proposed to effectively integrate the cross-level features, which can exploit the local and global contextual information. Finally, the outputs of CFMs are adaptively weighted by using the learned edge-aware feature, which are then used to produce multiple side-out segmentation maps. Experimental results on five widely adopted colonoscopy datasets show that our EFA-Net outperforms state-of-the-art polyp segmentation methods in terms of generalization and effectiveness. Our implementation code and segmentation maps will be publicly at https://***/taozh2017/EFANet. Copyright © 2023, The Authors. All rights reserved.

关键词： Image segmentation

Deep Multi-Model Fusion for Single-Image Dehazing

学校读者我要写书评

暂无评论

Deep Multi-Model Fusion for Single-Image Dehazing

International Conference on computer vision (ICCV)

作者： Zijun Deng Lei Zhu Xiaowei Hu Chi-Wing Fu Xuemiao Xu Qing Zhang Jing Qin Pheng-Ann Heng South China University of Technology Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institutes of Advanced Technology CAS The Chinese University of Hong Kong State Key Laboratory of Subtropical Building Science Guangdong Provincial Key Lab of Computational Intelligence and Cyberspace Information Sun Yat-sen University The Hong Kong Polytechnic University CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology CAS

ISBN: (数字)9781728148038

ISBN: (纸本)9781728148045

This paper presents a deep multi-model fusion network to attentively integrate multiple models to separate layers and boost the performance in single-image dehazing. To do so, we first formulate the attentional feature integration module to maximize the integration of the convolutional neural network (CNN) features at different CNN layers and generate the attentional multi-level integrated features (AMLIF). Then, from the AMLIF, we further predict a haze-free result for an atmospheric scattering model, as well as for four haze-layer separation models, and then fuse the results together to produce the final haze-free image. To evaluate the effectiveness of our method, we compare our network with several state-of-the-art methods on two widely-used dehazing benchmark datasets, as well as on two sets of real-world hazy images. Experimental results demonstrate clear quantitative and qualitative improvements of our method over the state-of-the-arts.

关键词： Atmospheric modeling Predictive models Scattering Computational modeling Neural networks computer vision Solid modeling