检索结果-内蒙古大学图书馆

Real-time correlation tracking via joint model compression and transfer

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Wang, Ning Zhou, Wengang Song, Yibing Ma, Chao Li, Houqiang CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System Department of Electronic Engineering and Information Science University of Science and Technology of China Hefei China Tencent AI Lab Shenzhen China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai China

Correlation filters (CF) have received considerable attention in visual tracking because of their computational efficiency. Leveraging deep features via off-the-shelf CNN models (e.g., VGG), CF trackers achieve state-of-the-art performance while consuming a large number of computing resources. This limits deep CF trackers to be deployed to many mobile platforms on which only a single-core CPU is available. In this paper, we propose to jointly compress and transfer off-the-shelf CNN models within a knowledge distillation framework. We formulate a CNN model pretrained from the image classification task as a teacher network, and distill this teacher network into a lightweight student network as the feature extractor to speed up CF trackers. In the distillation process, we propose a fidelity loss to enable the student network to maintain the representation capability of the teacher network. Meanwhile, we design a tracking loss to adapt the objective of the student network from object recognition to visual tracking. The distillation process is performed offline on multiple layers and adaptively updates the student network using a background-aware online learning scheme. Extensive experiments on five challenging datasets demonstrate that the lightweight student network accelerates the speed of state-of-the-art deep CF trackers to real-time on a single-core CPU while maintaining almost the same tracking accuracy. Copyright © 2019, The Authors. All rights reserved.

关键词： Object recognition

An attention-based word-level interaction model: Relation detection for knowledge base question answering

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Zhang, Hongzhi Xu, Guandong Liang, Xiao Huang, Tinglei Fu, Kun CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System Institute of Electronics Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China School of Software and Advanced Analytics University of Technology Sydney Australia

Relation detection plays a crucial role in Knowledge Base Question Answering (KBQA) because of the high variance of relation expression in the question. Traditional deep learning methods follow an encoding-comparing paradigm, where the question and the candidate relation are represented as vectors to compare their semantic similarity. Max- or average- pooling operation, which compresses the sequence of words into fixed-dimensional vectors, becomes the bottleneck of information. In this paper, we propose to learn attention-based word-level interactions between questions and relations to alleviate the bottleneck issue. Similar to the traditional models, the question and relation are firstly represented as sequences of vectors. Then, instead of merging the sequence into a single vector with pooling operation, soft alignments between words from the question and the relation are learned. The aligned words are subsequently compared with the convolutional neural network (CNN) and the comparison results are merged finally. Through performing the comparison on low-level representations, the attention-based word-level interaction model (ABWIM) relieves the information loss issue caused by merging the sequence into a fixed-dimensional vector before the comparison. The experimental results of relation detection on both SimpleQuestions and WebQuestions datasets show that ABWIM achieves state-of-the-art accuracy, demonstrating its effectiveness. Copyright © 2018, The Authors. All rights reserved.

关键词： Knowledge based systems

W-net: Simultaneous segmentation of multi-anatomical retinal structures using a multi-task deep neural network

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Zhao, Hongwei Peng, Chengtao Liu, Lei Li, Bin School of Information Science and Technology University of Science and Technology of China Hefei Anhui230022 China Department of Precision Machinery and Instrumentation University of Science and Technology of China HefeiAnhui230022 China CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei Anhui230026 China

Segmentation of multiple anatomical structures is of great importance in medical image analysis. In this study, we proposed a W-net to simultaneously segment both the optic disc (OD) and the exudates in retinal images based on the multi-task learning (MTL) scheme. We introduced a class-balanced loss and a multi-task weighted loss to alleviate the imbalanced problem and to improve the robustness and generalization property of the W-net. We demonstrated the effectiveness of our approach by applying five-fold cross-validation experiments on two public datasets e_ophtha_EX and DiaRetDb1. We achieved F1-score of 94.76% and 95.73% for OD segmentation, and 92.80% and 94.14% for exudates segmentation. To further prove the generalization property of the proposed method, we applied the trained model on the DRIONS-DB dataset for OD segmentation and on the MESSIDOR dataset for exudate segmentation. Our results demonstrated that by choosing the optimal weights of each task, the MTL based W-net outperformed separate models trained individually on each task. Code and pre-trained models will be available at: https://***/FundusResearch/MTL_for_OD_and_***. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep neural networks

Predictive auto-encoding network for blind stereoscopic image quality assessment

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Xu, Jiahua Zhou, Wei Chen, Zhibo Ling, Suiyi Le Callet, Patrick CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China quipe Image Perception et Interaction Laboratoire des Sciences du Numrique de Nantes Universit de Nantes Nantes44300 France

Stereoscopic image quality assessment (SIQA) has encountered non-trivial challenges due to the fast proliferation of 3D contents. In the past years, deep learning oriented SIQA methods have emerged and achieved spectacular performance compared to conventional algorithms which are only relied on extracting hand-crafted features. However, most existing deep SIQA evaluators are not specifically built for stereoscopic content and consider little prior domain knowledge of the 3D human visual system (HVS) in network design. In this paper, to better simulate the binocular rivalry phenomenon, we propose a Predictive Auto-encoDing Network (PAD-Net) for blind/No-Reference stereoscopic image quality assessment (NR-SIQA). The proposed encoder-decoder architecture is inspired by the predictive coding theory that the cognition system tries to match bottom-up visual signal with top-down predictions. Besides, we design the Siamese framework to mimic the binocular rivalry in the 3D HVS based on the likelihood and prior maps generated from the predictive coding process. Extensive experimental results on three publicly available stereoscopic image quality databases demonstrate that the devised approach outperforms state-of-the-art algorithms for predicting the perceptual quality of both symmetrically and asymmetrically distorted stereoscopic images with various distortion types. Copyright © 2019, The Authors. All rights reserved.

关键词： Network coding

Peer is Your Pillar: A Data-unbalanced Conditional GANs for Few-shot Image Generation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Li, Ziqiang Wang, Chaoyue Rui, Xue Xue, Chao Leng, Jiaxu Li, Bin Big Data and Decision Lab University of Science and Technology of China China The University of Sydney Australia JD Explore Academic China School of computer science Chongqing University of Posts and Telecommunications China CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System China

Few-shot image generation aims to train generative models using a small number of training images. When there are few images available for training (e.g. 10 images), Learning From Scratch (LFS) methods often generate images that closely resemble the training data while Transfer Learning (TL) methods try to improve performance by leveraging prior knowledge from GANs pre-trained on large-scale datasets. However, current TL methods may not allow for sufficient control over the degree of knowledge preservation from the source model, making them unsuitable for setups where the source and target domains are not closely related. To address this, we propose a novel pipeline called Peer is your Pillar (PIP), which combines a target few-shot dataset with a peer dataset to create a data-unbalanced conditional generation. Our approach includes a class embedding method that separates the class space from the latent space, and we use a direction loss based on pre-trained CLIP to improve image diversity. Experiments on various few-shot datasets demonstrate the advancement of the proposed PIP, especially reduces the training requirements of few-shot image generation. © 2023, CC BY.

关键词： Large dataset

Fuzzy-logic based adaptive weighting filter for strap-down inertial navigation systems

学校读者我要写书评

暂无评论

Fuzzy-logic based adaptive weighting filter for strap-down i...

World Congress on Intelligent Control and Automation (WCICA)

作者： Wenjun Lv Yu Kang Zhijun Li Yun-Bo Zhao Department of Automation & CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei Anhui Province China College of Automation Science and Engineering South China University of Technology Guangzhou Guangdong Province China College of Information Engineering Zhejiang University of Technology Hangzhou Zhejiang Province China

Strap-down inertial navigation systems are widely applicable in both military and civil industries. The outputs of gyroscope and accelerometer are polluted by noises. Different form the conventional technologies, the weighting filter presented in this work is superior to both the complementary filter and Kalman filter. Furthermore, to eliminate the negative effects brought by the variation of noise statistical characteristics, a fuzzy-logic based regulator is introduced to adjust the weight coefficient adaptively. Finally, experiments are conducted to validate the efficiency of the filter.

关键词： Noise Gyroscopes Accelerometers Kalman filters Accuracy Mathematical model Educational institutions

A simulator for swarm AUVs acoustic communication networking 11

学校读者我要写书评

暂无评论

A simulator for swarm AUVs acoustic communication networking

11th ACM International Conference on Underwater Networks and systems, WUWNet 2016

作者： Li, Guannan Liu, Jun Wang, Xue Xu, Hongli Cui, Jun-Hong Shenyang Institute of Automation CAS University of Chinese Academy of Sciences No. 114 Nanta Street Shenhe District Shenyang China College of Computer Science and Technology Jilin University State Key Laboratory of Robotics Key Laboratory of System Control and Information Processing Ministry of Education of China Changchun China Shenyang Institute of Automation CAS Northeast University No. 114 Nanta Street Shenhe District Shenyang China Shenyang Institute of Automation CAS No. 114 Nanta Street Shenhe District Shenyang China College of Computer Science and Technology Jilin University Changchun China Underwater Sensor Network Lab. University of Connecticut StorrsCT06269 United States

ISBN: (纸本)9781450346375

This paper presents a simulator for swarm operations designed to verify algorithms for a swarm of autonomous underwater robots (AUVs), specifically for constructing an underwater communication network with AUVs carrying acoustic communication devices. This simulator consists of three nodes: a virtual vehicle node (VV), a virtual environment node (VE), and a visual showing node (VS). The modular design treats AUV models as a combination of virtual equipment. An expert acoustic communication simulator is embedded in this simulator, to simulate scenarios with dynamic acoustic communication nodes. The several simulations we have performed demonstrate that this simulator is easy to use and can be further improved.

关键词： Simulators

A generalization theory based on independent and task-identically distributed assumption

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Zheng, Guanhua Sang, Jitao Li, Houqiang Yu, Jian Xu, Changsheng University of Science and Technology of China School of Computer and Information Technology Beijing Key Laboratory of Traffic Data Analysis and Mining Beijing Jiaotong University Beijing100044 China Chinese Academy of Sciences Key Laboratory of Technology in Geo-Spatial Information Processing and Application System Hefei230026 China National Lab of Pattern Recognition Institute of Automation CAS Beijing100190 China University of Chinese Academy of Sciences

—Existing generalization theories analyze the generalization performance mainly based on the model complexity and training process. The ignorance of the task properties, which results from the widely used IID assumption, makes these theories fail to interpret many generalization phenomena or guide practical learning tasks. In this paper, we propose a new Independent and Task-Identically Distributed (ITID) assumption, to consider the task properties into the data generating process. The derived generalization bound based on the ITID assumption identifies the significance of hypothesis invariance in guaranteeing generalization performance. Based on the new bound, we introduce a practical invariance enhancement algorithm from the perspective of modifying data distributions. Finally, we verify the algorithm and theorems in the context of image classification task on both toy and real-world datasets. The experimental results demonstrate the reasonableness of the ITID assumption and the effectiveness of new generalization theory in improving practical generalization performance. Copyright © 2019, The Authors. All rights reserved.

关键词： Classification (of information)

An end-to-end foreground-aware network for person re-identification

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Liu, Yiheng Zhou, Wengang Liu, Jianzhuang Qi, Guojun Tian, Qi Li, Houqiang CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System Department of Electronic Engineering and Information Science University of Science and Technology of China Hefei230027 China Noah’s Ark Lab Huawei Technologies Company Limited Shenzhen518129 China Huawei Cloud EI Product Department Cloud & AI Huawei Technologies

Person re-identification is a crucial task of identifying pedestrians of interest across multiple surveillance camera views. For person re-identification, a pedestrian is usually represented with features extracted from a rectangular image region that inevitably contains the scene background, which incurs ambiguity to distinguish different pedestrians and degrades the accuracy. Thus, we propose an end-to-end foreground-aware network to discriminate against the foreground from the background by learning a soft mask for person re-identification. In our method, in addition to the pedestrian ID as supervision for the foreground, we introduce the camera ID of each pedestrian image for background modeling. The foreground branch and the background branch are optimized collaboratively. By presenting a target attention loss, the pedestrian features extracted from the foreground branch become more insensitive to backgrounds, which greatly reduces the negative impact of changing backgrounds on pedestrian matching across different camera views. Notably, in contrast to existing methods, our approach does not require an additional dataset to train a human landmark detector or a segmentation model for locating the background regions. The experimental results conducted on three challenging datasets, i.e., Market-1501, DukeMTMC-reID, and MSMT17, demonstrate the effectiveness of our approach. Copyright © 2019, The Authors. All rights reserved.

关键词： Cameras