Filters








147 Hits in 1.3 sec

Discrete All-Pay Bidding Games [article]

Michael Menz, Justin Wang, Jiyang Xie
2015 arXiv   pre-print
In an all-pay auction, only one bidder wins but all bidders must pay the auctioneer. All-pay bidding games arise from attaching a similar bidding structure to traditional combinatorial games to determine which player moves next. In contrast to the established theory of single-pay bidding games, optimal play involves choosing bids from some probability distribution that will guarantee a minimum probability of winning. In this manner, all-pay bidding games wed the underlying concepts of economic
more » ... nd combinatorial games. We present several results on the structures of optimal strategies in these games. We then give a fast algorithm for computing such strategies for a large class of all-pay bidding games. The methods presented provide a framework for further development of the theory of all-pay bidding games.
arXiv:1504.02799v2 fatcat:xmyimgswkvfobb73nyk35jc5wy

Searching for Network Width with Bilaterally Coupled Network [article]

Xiu Su, Shan You, Jiyang Xie, Fei Wang, Chen Qian, Changshui Zhang, Chang Xu
2022 arXiv   pre-print
Searching for a more compact network width recently serves as an effective way of channel pruning for the deployment of convolutional neural networks (CNNs) under hardware constraints. To fulfill the searching, a one-shot supernet is usually leveraged to efficiently evaluate the performance different network widths. However, current methods mainly follow a unilaterally augmented (UA) principle for the evaluation of each width, which induces the training unfairness of channels in supernet. In
more » ... s paper, we introduce a new supernet called Bilaterally Coupled Network (BCNet) to address this issue. In BCNet, each channel is fairly trained and responsible for the same amount of network widths, thus each network width can be evaluated more accurately. Besides, we propose to reduce the redundant search space and present the BCNetV2 as the enhanced supernet to ensure rigorous training fairness over channels. Furthermore, we leverage a stochastic complementary strategy for training the BCNet, and propose a prior initial population sampling method to boost the performance of the evolutionary search. We also propose the first open-source width benchmark on macro structures named Channel-Bench-Macro for the better comparison of width search algorithms. Extensive experiments on benchmark CIFAR-10 and ImageNet datasets indicate that our method can achieve state-of-the-art or competing performance over other baseline methods. Moreover, our method turns out to further boost the performance of NAS models by refining their network widths. For example, with the same FLOPs budget, our obtained EfficientNet-B0 achieves 77.53% Top-1 accuracy on ImageNet dataset, surpassing the performance of original setting by 0.65%.
arXiv:2203.13714v1 fatcat:cjnvo6ez45a7hc57xoehmialmi

SEA: A Combined Model for Heat Demand Prediction [article]

Jiyang Xie, Jiaxin Guo, Zhanyu Ma, Jing-Hao Xue, Qie Sun, Hailong Li, Jun Guo
2018 arXiv   pre-print
Heat demand prediction is a prominent research topic in the area of intelligent energy networks. It has been well recognized that periodicity is one of the important characteristics of heat demand. Seasonal-trend decomposition based on LOESS (STL) algorithm can analyze the periodicity of a heat demand series, and decompose the series into seasonal and trend components. Then, predicting the seasonal and trend components respectively, and combining their predictions together as the heat demand
more » ... diction is a possible way to predict heat demand. In this paper, STL-ENN-ARIMA (SEA), a combined model, was proposed based on the combination of the Elman neural network (ENN) and the autoregressive integrated moving average (ARIMA) model, which are commonly applied to heat demand prediction. ENN and ARIMA are used to predict seasonal and trend components, respectively. Experimental results demonstrate that the proposed SEA model has a promising performance.
arXiv:1808.00331v1 fatcat:p6utovn3pfelhdwvz37yahm4t4

Mobile big data analysis with machine learning [article]

Jiyang Xie, Zeyu Song, Yupeng Li, Zhanyu Ma
2020 arXiv   pre-print
This paper investigates to identify the requirement and the development of machine learning-based mobile big data analysis through discussing the insights of challenges in the mobile big data (MBD). Furthermore, it reviews the state-of-the-art applications of data analysis in the area of MBD. Firstly, we introduce the development of MBD. Secondly, the frequently adopted methods of data analysis are reviewed. Three typical applications of MBD analysis, namely wireless channel modeling, human
more » ... ne and offline behavior analysis, and speech recognition in the internet of vehicles, are introduced respectively. Finally, we summarize the main challenges and future development directions of mobile big data analysis.
arXiv:1808.00803v2 fatcat:42l62ikc2rhd3bzuao25hhrwgm

Impacts of Weather Conditions on District Heat System [article]

Jiyang Xie, Zhanyu Ma, Jun Guo
2020 arXiv   pre-print
Xie, Z. Ma models attract more and more attention in the prediction of heat demand, due to its unique advantages, such as the ability to reflect the sociological behaviors of consumers.  ... 
arXiv:1808.00961v2 fatcat:n52evuhz4ff2bl63lvnroikfxe

Unsupervised Person Re-identification via Simultaneous Clustering and Consistency Learning [article]

Junhui Yin, Jiayan Qiu, Siqing Zhang, Jiyang Xie, Zhanyu Ma, Jun Guo
2021 arXiv   pre-print
Unsupervised person re-identification (re-ID) has become an important topic due to its potential to resolve the scalability problem of supervised re-ID models. However, existing methods simply utilize pseudo labels from clustering for supervision and thus have not yet fully explored the semantic information in data itself, which limits representation capabilities of learned models. To address this problem, we design a pretext task for unsupervised re-ID by learning visual consistency from still
more » ... images and temporal consistency during training process, such that the clustering network can separate the images into semantic clusters automatically. Specifically, the pretext task learns semantically meaningful representations by maximizing the agreement between two encoded views of the same image via a consistency loss in latent space. Meanwhile, we optimize the model by grouping the two encoded views into same cluster, thus enhancing the visual consistency between views. Experiments on Market-1501, DukeMTMC-reID and MSMT17 datasets demonstrate that our proposed approach outperforms the state-of-the-art methods by large margins.
arXiv:2104.00202v1 fatcat:eyj7bpn3zvc3zmjchl5iv5itze

Cross-layer Navigation Convolutional Neural Network for Fine-grained Visual Classification [article]

Chenyu Guo, Jiyang Xie, Kongming Liang, Xian Sun, Zhanyu Ma
2021 arXiv   pre-print
Xie 1 , Kongming Liang 1 , Xian Sun 2 , Zhanyu Ma 1  ...  proposed method I obtains significant improvements on all the three datasets among the referred methods.The referred methods listed in Conference'17, July 2017, Washington, DC, USA Chenyu Guo 1 , Jiyang  ... 
arXiv:2106.10920v1 fatcat:yj2d4zb5izdtvj35wdu65v2zje

Structured DropConnect for Uncertainty Inference in Image Classification [article]

Wenqing Zheng, Jiyang Xie, Weidong Liu, Zhanyu Ma
2021 arXiv   pre-print
Xie [27] proposed advanced dropout, a model-free methodology, to mitigate overfitting and improve the performance of DNNs.  ... 
arXiv:2106.08624v2 fatcat:77acuk3yj5bi7eprqo7g6xuc2a

ViTAS: Vision Transformer Architecture Search [article]

Xiu Su, Shan You, Jiyang Xie, Mingkai Zheng, Fei Wang, Chen Qian, Changshui Zhang, Xiaogang Wang, Chang Xu
2021 arXiv   pre-print
Vision transformers (ViTs) inherited the success of NLP but their structures have not been sufficiently investigated and optimized for visual tasks. One of the simplest solutions is to directly search the optimal one via the widely used neural architecture search (NAS) in CNNs. However, we empirically find this straightforward adaptation would encounter catastrophic failures and be frustratingly unstable for the training of superformer. In this paper, we argue that since ViTs mainly operate on
more » ... oken embeddings with little inductive bias, imbalance of channels for different architectures would worsen the weight-sharing assumption and cause the training instability as a result. Therefore, we develop a new cyclic weight-sharing mechanism for token embeddings of the ViTs, which enables each channel could more evenly contribute to all candidate architectures. Besides, we also propose identity shifting to alleviate the many-to-one issue in superformer and leverage weak augmentation and regularization techniques for more steady training empirically. Based on these, our proposed method, ViTAS, has achieved significant superiority in both DeiT- and Twins-based ViTs. For example, with only 1.4G FLOPs budget, our searched architecture has 3.3% ImageNet-1k accuracy than the baseline DeiT. With 3.0G FLOPs, our results achieve 82.0% accuracy on ImageNet-1k, and 45.9% mAP on COCO2017 which is 2.4% superior than other ViTs.
arXiv:2106.13700v2 fatcat:n5uxtotowvhz7cxmzwtsmxo3qe

The Role of Data Analysis in the Development of Intelligent Energy Networks [article]

Zhanyu Ma, Jiyang Xie, Hailong Li, Qie Sun, Zhongwei Si, Jianhua Zhang, Jun Guo
2017 arXiv   pre-print
Data analysis plays an important role in the development of intelligent energy networks (IENs). This article reviews and discusses the application of data analysis methods for energy big data. The installation of smart energy meters has provided a huge volume of data at different time resolutions, suggesting data analysis is required for clustering, demand forecasting, energy generation optimization, energy pricing, monitoring and diagnostics. The currently adopted data analysis technologies
more » ... IENs include pattern recognition, machine learning, data mining, statistics methods, etc. However, existing methods for data analysis cannot fully meet the requirements for processing the big data produced by the IENs and, therefore, more comprehensive data analysis methods are needed to handle the increasing amount of data and to mine more valuable information.
arXiv:1705.11132v1 fatcat:pumkryrgrzayrj55edess6wgsm

Weakly Supervised Attention Pyramid Convolutional Neural Network for Fine-Grained Visual Classification [article]

Yifeng Ding, Shaoguo Wen, Jiyang Xie, Dongliang Chang, Zhanyu Ma, Zhongwei Si, Haibin Ling
2020 arXiv   pre-print
Classifying the sub-categories of an object from the same super-category (e.g. bird species, car and aircraft models) in fine-grained visual classification (FGVC) highly relies on discriminative feature representation and accurate region localization. Existing approaches mainly focus on distilling information from high-level features. In this paper, however, we show that by integrating low-level information (e.g. color, edge junctions, texture patterns), performance can be improved with
more » ... feature representation and accurately located discriminative regions. Our solution, named Attention Pyramid Convolutional Neural Network (AP-CNN), consists of a) a pyramidal hierarchy structure with a top-down feature pathway and a bottom-up attention pathway, and hence learns both high-level semantic and low-level detailed feature representation, and b) an ROI guided refinement strategy with ROI guided dropblock and ROI guided zoom-in, which refines features with discriminative local regions enhanced and background noises eliminated. The proposed AP-CNN can be trained end-to-end, without the need of additional bounding box/part annotations. Extensive experiments on three commonly used FGVC datasets (CUB-200-2011, Stanford Cars, and FGVC-Aircraft) demonstrate that our approach can achieve state-of-the-art performance. Code available at
arXiv:2002.03353v1 fatcat:irydzwjpeffafoa246fgt5dcaa

Shoe-print image retrieval with multi-part weighted CNN

Zhanyu Ma, Yifeng Ding, Shaoguo Wen, Jiyang Xie, Yifeng Jin, Zhongwei Si, Haining Wang
2019 IEEE Access  
JIYANG XIE received the B.E. degree in information engineering from the Beijing University of Posts and Telecommunications (BUPT), China, in 2017, where he is currently pursuing the Ph.D. degree.  ... 
doi:10.1109/access.2019.2914455 fatcat:ua7w2jylfvaz7oj33pxg4odb5a

DS-UI: Dual-Supervised Mixture of Gaussian Mixture Models for Uncertainty Inference [article]

Jiyang Xie and Zhanyu Ma and Jing-Hao Xue and Guoqiang Zhang and Jun Guo
2020 arXiv   pre-print
This paper proposes a dual-supervised uncertainty inference (DS-UI) framework for improving Bayesian estimation-based uncertainty inference (UI) in deep neural network (DNN)-based image recognition. In the DS-UI, we combine the classifier of a DNN, i.e., the last fully-connected (FC) layer, with a mixture of Gaussian mixture models (MoGMM) to obtain an MoGMM-FC layer. Unlike existing UI methods for DNNs, which only calculate the means or modes of the DNN outputs' distributions, the proposed
more » ... M-FC layer acts as a probabilistic interpreter for the features that are inputs of the classifier to directly calculate the probability density of them for the DS-UI. In addition, we propose a dual-supervised stochastic gradient-based variational Bayes (DS-SGVB) algorithm for the MoGMM-FC layer optimization. Unlike conventional SGVB and optimization algorithms in other UI methods, the DS-SGVB not only models the samples in the specific class for each Gaussian mixture model (GMM) in the MoGMM, but also considers the negative samples from other classes for the GMM to reduce the intra-class distances and enlarge the inter-class margins simultaneously for enhancing the learning ability of the MoGMM-FC layer in the DS-UI. Experimental results show the DS-UI outperforms the state-of-the-art UI methods in misclassification detection. We further evaluate the DS-UI in open-set out-of-domain/-distribution detection and find statistically significant improvements. Visualizations of the feature spaces demonstrate the superiority of the DS-UI.
arXiv:2011.08595v1 fatcat:rcoe4x4axrbqznr3cje3ggl3gq

Quantitative Comparisons of Linked Color Imaging and White-Light Colonoscopy for Colorectal Polyp Analysis [article]

Xinran Wei, Jiyang Xie, Wenrui He, Min Min, Zhanyu Ma, Jun Guo
2018 arXiv   pre-print
The performance of imaging techniques has an important influence on the clinical diagnostic strategy of colorectal cancer. Linked color imaging (LCI) by laser endoscopy is a recently developed techniques, and its advantage in improving the analysis accuracy of colorectal polyps over white-light (WL) endoscopy has been demonstrated in previous clinical studies. However, there are no objective criteria to evaluate and compare the aforementioned endoscopy methods. This paper presents a new
more » ... n, namely entropy of color gradients image (ECGI), which is based on color gradients distribution and provides a comprehensive and objective evaluating indicator of the performance of colorectal images. Our method extracts the color gradient image pairs of 143 colonoscopy polyps in the LCI-PairedColon database, which are generated with WL and LCI conditions, respectively. Then, we apply the morphological method to fix the deviation of light-reflecting regions, and the ECGI scores of sample pairs are calculated. Experimental results show that the average ECGI scores of LCI images (5.7071) were significantly higher than that of WL (4.6093). This observation is consistent with the clinical studies. Therefore, the effectiveness of the proposed criterion is demonstrated.
arXiv:1807.11913v1 fatcat:i2p5bvumljbvpbvcv2snm6ltby

GPCA: A Probabilistic Framework for Gaussian Process Embedded Channel Attention [article]

Jiyang Xie, Dongliang Chang, Zhanyu Ma, Guoqiang Zhang, Jun Guo
2021 arXiv   pre-print
Channel attention mechanisms have been commonly applied in many visual tasks for effective performance improvement. It is able to reinforce the informative channels as well as to suppress the useless channels. Recently, different channel attention modules have been proposed and implemented in various ways. Generally speaking, they are mainly based on convolution and pooling operations. In this paper, we propose Gaussian process embedded channel attention (GPCA) module and further interpret the
more » ... hannel attention schemes in a probabilistic way. The GPCA module intends to model the correlations among the channels, which are assumed to be captured by beta distributed variables. As the beta distribution cannot be integrated into the end-to-end training of convolutional neural networks (CNNs) with a mathematically tractable solution, we utilize an approximation of the beta distribution to solve this problem. To specify, we adapt a Sigmoid-Gaussian approximation, in which the Gaussian distributed variables are transferred into the interval [0,1]. The Gaussian process is then utilized to model the correlations among different channels. In this case, a mathematically tractable solution is derived. The GPCA module can be efficiently implemented and integrated into the end-to-end training of the CNNs. Experimental results demonstrate the promising performance of the proposed GPCA module. Codes are available at https://github.com/PRIS-CV/GPCA.
arXiv:2003.04575v2 fatcat:ctwpkxgcanbndedz72u46bftyy
« Previous Showing results 1 — 15 out of 147 results