Models, code, and papers for "Te Zhang":

Boosted Zero-Shot Learning with Semantic Correlation Regularization

Jul 25, 2017
Te Pi, Xi Li, Zhongfei, Zhang

We study zero-shot learning (ZSL) as a transfer learning problem, and focus on the two key aspects of ZSL, model effectiveness and model adaptation. For effective modeling, we adopt the boosting strategy to learn a zero-shot classifier from weak models to a strong model. For adaptable knowledge transfer, we devise a Semantic Correlation Regularization (SCR) approach to regularize the boosted model to be consistent with the inter-class semantic correlations. With SCR embedded in the boosting objective, and with a self-controlled sample selection for learning robustness, we propose a unified framework, Boosted Zero-shot classification with Semantic Correlation Regularization (BZ-SCR). By balancing the SCR-regularized boosted model selection and the self-controlled sample selection, BZ-SCR is capable of capturing both discriminative and adaptable feature-to-class semantic alignments, while ensuring the reliability and adaptability of the learned samples. The experiments on two ZSL datasets show the superiority of BZ-SCR over the state-of-the-arts.

* 7 pages; IJCAI 2017 

  Click for Model/Code and Paper
Multi-View Fuzzy Logic System with the Cooperation between Visible and Hidden Views

Jul 23, 2018
Te Zhang, Zhaohong Deng, Dongrui Wu, Shitong Wang

Multi-view datasets are frequently encountered in learning tasks, such as web data mining and multimedia information analysis. Given a multi-view dataset, traditional learning algorithms usually decompose it into several single-view datasets, from each of which a single-view model is learned. In contrast, a multi-view learning algorithm can achieve better performance by cooperative learning on the multi-view data. However, existing multi-view approaches mainly focus on the views that are visible and ignore the hidden information behind the visible views, which usually contains some intrinsic information of the multi-view data, or vice versa. To address this problem, this paper proposes a multi-view fuzzy logic system, which utilizes both the hidden information shared by the multiple visible views and the information of each visible view. Extensive experiments were conducted to validate its effectiveness.


  Click for Model/Code and Paper
Spatial Shortcut Network for Human Pose Estimation

Apr 05, 2019
Te Qi, Bayram Bayramli, Usman Ali, Qinchuan Zhang, Hongtao Lu

Like many computer vision problems, human pose estimation is a challenging problem in that recognizing a body part requires not only information from local area but also from areas with large spatial distance. In order to spatially pass information, large convolutional kernels and deep layers have been normally used, introducing high computation cost and large parameter space. Luckily for pose estimation, human body is geometrically structured in images, enabling modeling of spatial dependency. In this paper, we propose a spatial shortcut network for pose estimation task, where information is easier to flow spatially. We evaluate our model with detailed analyses and present its outstanding performance with smaller structure.

* 12 pages 

  Click for Model/Code and Paper
Multi-View Fuzzy Clustering with The Alternative Learning between Shared Hidden Space and Partition

Aug 12, 2019
Zhaohong Deng, Chen Cui, Peng Xu, Ling Liang, Haoran Chen, Te Zhang, Shitong Wang

As the multi-view data grows in the real world, multi-view clus-tering has become a prominent technique in data mining, pattern recognition, and machine learning. How to exploit the relation-ship between different views effectively using the characteristic of multi-view data has become a crucial challenge. Aiming at this, a hidden space sharing multi-view fuzzy clustering (HSS-MVFC) method is proposed in the present study. This method is based on the classical fuzzy c-means clustering model, and obtains associ-ated information between different views by introducing shared hidden space. Especially, the shared hidden space and the fuzzy partition can be learned alternatively and contribute to each other. Meanwhile, the proposed method uses maximum entropy strategy to control the weights of different views while learning the shared hidden space. The experimental result shows that the proposed multi-view clustering method has better performance than many related clustering methods.

* This paper has been submitted to IEEE Transactions on Cybnetics in Apr. 8th 2019 

  Click for Model/Code and Paper
Multi-view Clustering with the Cooperation of Visible and Hidden Views

Aug 12, 2019
Zhaohong Deng, Ruixiu Liu, Te Zhang, Peng Xu, Kup-Sze Choi, Bin Qin, Shitong Wang

Multi-view data are becoming common in real-world modeling tasks and many multi-view data clustering algorithms have thus been proposed. The existing algorithms usually focus on the cooperation of different views in the original space but neglect the influence of the hidden information among these different visible views, or they only consider the hidden information between the views. The algorithms are therefore not efficient since the available information is not fully excavated, particularly the otherness information in different views and the consistency information between them. In practice, the otherness and consistency information in multi-view data are both very useful for effective clustering analyses. In this study, a Multi-View clustering algorithm developed with the Cooperation of Visible and Hidden views, i.e., MV-Co-VH, is proposed. The MV-Co-VH algorithm first projects the multiple views from different visible spaces to the common hidden space by using the non-negative matrix factorization (NMF) strategy to obtain the common hidden view data. Collaborative learning is then implemented in the clustering procedure based on the visible views and the shared hidden view. The results of extensive experiments on UCI multi-view datasets and real-world image multi-view datasets show that the clustering performance of the proposed algorithm is competitive with or even better than that of the existing algorithms.

* This paper has been submitted to IEEE TKDE in Jun. 2019 

  Click for Model/Code and Paper
Concise Fuzzy System Modeling Integrating Soft Subspace Clustering and Sparse Learning

Apr 24, 2019
Peng Xu, Zhaohong Deng, Chen Cui, Te Zhang, Kup-Sze Choi, Gu Suhang, Jun Wang, ShiTong Wang

The superior interpretability and uncertainty modeling ability of Takagi-Sugeno-Kang fuzzy system (TSK FS) make it possible to describe complex nonlinear systems intuitively and efficiently. However, classical TSK FS usually adopts the whole feature space of the data for model construction, which can result in lengthy rules for high-dimensional data and lead to degeneration in interpretability. Furthermore, for highly nonlinear modeling task, it is usually necessary to use a large number of rules which further weakens the clarity and interpretability of TSK FS. To address these issues, a concise zero-order TSK FS construction method, called ESSC-SL-CTSK-FS, is proposed in this paper by integrating the techniques of enhanced soft subspace clustering (ESSC) and sparse learning (SL). In this method, ESSC is used to generate the antecedents and various sparse subspace for different fuzzy rules, whereas SL is used to optimize the consequent parameters of the fuzzy rules, based on which the number of fuzzy rules can be effectively reduced. Finally, the proposed ESSC-SL-CTSK-FS method is used to construct con-cise zero-order TSK FS that can explain the scenes in high-dimensional data modeling more clearly and easily. Experiments are conducted on various real-world datasets to confirm the advantages.


  Click for Model/Code and Paper
Improving Neural Relation Extraction with Positive and Unlabeled Learning

Nov 28, 2019
Zhengqiu He, Wenliang Chen, Yuyi Wang, Wei zhang, Guanchun Wang, Min Zhang

We present a novel approach to improve the performance of distant supervision relation extraction with Positive and Unlabeled (PU) Learning. This approach first applies reinforcement learning to decide whether a sentence is positive to a given relation, and then positive and unlabeled bags are constructed. In contrast to most previous studies, which mainly use selected positive instances only, we make full use of unlabeled instances and propose two new representations for positive and unlabeled bags. These two representations are then combined in an appropriate way to make bag-level prediction. Experimental results on a widely used real-world dataset demonstrate that this new approach indeed achieves significant and consistent improvements as compared to several competitive baselines.

* 8 pages, AAAI-2020 

  Click for Model/Code and Paper
Average-case Analysis of the Assignment Problem with Independent Preferences

Jun 01, 2019
Yansong Gao, Jie Zhang

The fundamental assignment problem is in search of welfare maximization mechanisms to allocate items to agents when the private preferences over indivisible items are provided by self-interested agents. The mainstream mechanism \textit{Random Priority} is asymptotically the best mechanism for this purpose, when comparing its welfare to the optimal social welfare using the canonical \textit{worst-case approximation ratio}. Despite its popularity, the efficiency loss indicated by the worst-case ratio does not have a constant bound. Recently, [Deng, Gao, Zhang 2017] show that when the agents' preferences are drawn from a uniform distribution, its \textit{average-case approximation ratio} is upper bounded by 3.718. They left it as an open question of whether a constant ratio holds for general scenarios. In this paper, we offer an affirmative answer to this question by showing that the ratio is bounded by $1/\mu$ when the preference values are independent and identically distributed random variables, where $\mu$ is the expectation of the value distribution. This upper bound also improves the upper bound of 3.718 in [Deng, Gao, Zhang 2017] for the Uniform distribution. Moreover, under mild conditions, the ratio has a \textit{constant} bound for any independent random values. En route to these results, we develop powerful tools to show the insights that in most instances the efficiency loss is small.

* To appear in IJCAI 2019 

  Click for Model/Code and Paper
Instance-Level Segmentation for Autonomous Driving with Deep Densely Connected MRFs

Apr 27, 2016
Ziyu Zhang, Sanja Fidler, Raquel Urtasun

Our aim is to provide a pixel-wise instance-level labeling of a monocular image in the context of autonomous driving. We build on recent work [Zhang et al., ICCV15] that trained a convolutional neural net to predict instance labeling in local image patches, extracted exhaustively in a stride from an image. A simple Markov random field model using several heuristics was then proposed in [Zhang et al., ICCV15] to derive a globally consistent instance labeling of the image. In this paper, we formulate the global labeling problem with a novel densely connected Markov random field and show how to encode various intuitive potentials in a way that is amenable to efficient mean field inference [Kr\"ahenb\"uhl et al., NIPS11]. Our potentials encode the compatibility between the global labeling and the patch-level predictions, contrast-sensitive smoothness as well as the fact that separate regions form different instances. Our experiments on the challenging KITTI benchmark [Geiger et al., CVPR12] demonstrate that our method achieves a significant performance boost over the baseline [Zhang et al., ICCV15].


  Click for Model/Code and Paper
Experience-driven Networking: A Deep Reinforcement Learning based Approach

Jan 17, 2018
Zhiyuan Xu, Jian Tang, Jingsong Meng, Weiyi Zhang, Yanzhi Wang, Chi Harold Liu, Dejun Yang

Modern communication networks have become very complicated and highly dynamic, which makes them hard to model, predict and control. In this paper, we develop a novel experience-driven approach that can learn to well control a communication network from its own experience rather than an accurate mathematical model, just as a human learns a new skill (such as driving, swimming, etc). Specifically, we, for the first time, propose to leverage emerging Deep Reinforcement Learning (DRL) for enabling model-free control in communication networks; and present a novel and highly effective DRL-based control framework, DRL-TE, for a fundamental networking problem: Traffic Engineering (TE). The proposed framework maximizes a widely-used utility function by jointly learning network environment and its dynamics, and making decisions under the guidance of powerful Deep Neural Networks (DNNs). We propose two new techniques, TE-aware exploration and actor-critic-based prioritized experience replay, to optimize the general DRL framework particularly for TE. To validate and evaluate the proposed framework, we implemented it in ns-3, and tested it comprehensively with both representative and randomly generated network topologies. Extensive packet-level simulation results show that 1) compared to several widely-used baseline methods, DRL-TE significantly reduces end-to-end delay and consistently improves the network utility, while offering better or comparable throughput; 2) DRL-TE is robust to network changes; and 3) DRL-TE consistently outperforms a state-ofthe-art DRL method (for continuous control), Deep Deterministic Policy Gradient (DDPG), which, however, does not offer satisfying performance.

* 9 pages, 12 figures, paper is accepted as a conference paper at IEEE Infocom 2018 

  Click for Model/Code and Paper
Inference with Causal Independence in the CPSC Network

Feb 20, 2013
Nevin Lianwen Zhang

This paper reports experiments with the causal independence inference algorithm proposed by Zhang and Poole (1994b) on the CPSC network created by Pradhan et al. (1994). It is found that the algorithm is able to answer 420 of the 422 possible zero-observation queries, 94 of 100 randomly generated five-observation queries, 87 of 100 randomly generated ten-observation queries, and 69 of 100 randomly generated twenty-observation queries.

* Appears in Proceedings of the Eleventh Conference on Uncertainty in Artificial Intelligence (UAI1995) 

  Click for Model/Code and Paper
Supervised and Semi-Supervised Text Categorization using LSTM for Region Embeddings

May 26, 2016
Rie Johnson, Tong Zhang

One-hot CNN (convolutional neural network) has been shown to be effective for text categorization (Johnson & Zhang, 2015). We view it as a special case of a general framework which jointly trains a linear model with a non-linear feature generator consisting of `text region embedding + pooling'. Under this framework, we explore a more sophisticated region embedding method using Long Short-Term Memory (LSTM). LSTM can embed text regions of variable (and possibly large) sizes, whereas the region size needs to be fixed in a CNN. We seek effective and efficient use of LSTM for this purpose in the supervised and semi-supervised settings. The best results were obtained by combining region embeddings in the form of LSTM and convolution layers trained on unlabeled data. The results indicate that on this task, embeddings of text regions, which can convey complex concepts, are more useful than embeddings of single words in isolation. We report performances exceeding the previous best results on four benchmark datasets.


  Click for Model/Code and Paper
Self-driving scale car trained by Deep reinforcement Learning

Sep 08, 2019
Qi Zhang, Tao Du

This paper considers the problem of self-driving algorithm based on deep learning. This is a hot topic because self-driving is the most important application field of artificial intelligence. Existing work focused on deep learning which has the ability to learn end-to-end self-driving control directly from raw sensory data, but this method is just a mapping between images and driving. We prefer deep reinforcement learning to train a self-driving car in a virtual simulation environment created by Unity and then migrate to reality. Deep reinforcement learning makes the machine own the driving descision-making ability like human. The virtual to realistic training method can efficiently handle the problem that reinforcement learning requires reward from the environment which probably cause cars damge. We have derived a theoretical model and analysis on how to use Deep Q-learning to control a car to drive. We have carried out simulations in the Unity virtual environment for evaluating the performance. Finally, we successfully migrate te model to the real world and realize self-driving.


  Click for Model/Code and Paper
Dimension Correction for Hierarchical Latent Class Models

Dec 12, 2012
Tomas Kocka, Nevin Lianwen Zhang

Model complexity is an important factor to consider when selecting among graphical models. When all variables are observed, the complexity of a model can be measured by its standard dimension, i.e. the number of independent parameters. When hidden variables are present, however, standard dimension might no longer be appropriate. One should instead use effective dimension (Geiger et al. 1996). This paper is concerned with the computation of effective dimension. First we present an upper bound on the effective dimension of a latent class (LC) model. This bound is tight and its computation is easy. We then consider a generalization of LC models called hierarchical latent class (HLC) models (Zhang 2002). We show that the effective dimension of an HLC model can be obtained from the effective dimensions of some related LC models. We also demonstrate empirically that using effective dimension in place of standard dimension improves the quality of models learned from data.

* Appears in Proceedings of the Eighteenth Conference on Uncertainty in Artificial Intelligence (UAI2002) 

  Click for Model/Code and Paper
Phase Contrast Microscopy Cell PopulationSegmentation: A Survey

Nov 25, 2019
Lin Zhang

Phase contrast microscopy (PCM) has been widely used in biomedicine research, which allows users to observe objectives without staining or killing them. One important related research is to employ PCM to monitor live cells. How to segment cell populations in obtained PCM images gains more and more attention as its a critical step for downstream applications, such as cell tracking, cell classification and others. Many papers have been published to deal with this problem from different perspectives. In this paper we aim to present a comprehensive review on the development of PCM cell population segmentation.


  Click for Model/Code and Paper
Automatic Ensemble Learning for Online Influence Maximization

Nov 25, 2019
Xiaojin Zhang

We consider the problem of selecting a seed set to maximize the expected number of influenced nodes in the social network, referred to as the \textit{influence maximization} (IM) problem. We assume that the topology of the social network is prescribed while the influence probabilities among edges are unknown. In order to learn the influence probabilities and simultaneously maximize the influence spread, we consider the tradeoff between exploiting the current estimation of the influence probabilities to ensure certain influence spread and exploring more nodes to learn better about the influence probabilities. The exploitation-exploration trade-off is the core issue in the multi-armed bandit (MAB) problem. If we regard the influence spread as the reward, then the IM problem could be reduced to the combinatorial multi-armed bandits. At each round, the learner selects a limited number of seed nodes in the social network, then the influence spreads over the network according to the real influence probabilities. The learner could observe the activation status of the edge if and only if its start node is influenced, which is referred to as the edge-level semi-bandit feedback. Two classical bandit algorithms including Thompson Sampling and Epsilon Greedy are used to solve this combinatorial problem. To ensure the robustness of these two algorithms, we use an automatic ensemble learning strategy, which combines the exploration strategy with exploitation strategy. The ensemble algorithm is self-adaptive regarding that the probability of each algorithm could be adjusted based on the historical performance of the algorithm. Experimental evaluation illustrates the effectiveness of the automatically adjusted hybridization of exploration algorithm with exploitation algorithm.


  Click for Model/Code and Paper
A*SLAM: A Dual Fisheye Stereo Edge SLAM

Nov 11, 2019
Guoxuan Zhang

This paper proposes an A*SLAM system that features combining two sets of fisheye stereo cameras and taking the image edge as the SLAM features. The dual fisheye stereo camera sets cover the full environmental view of the SLAM system. From each fisheye stereo image pair, a panorama depth image can be directly extracted for initializing the SLAM feature. The edge feature is an illumination invariant feature. The paper presents a method of the edge-based simultaneous localization and mapping process using both the normal and inverted images interchangeably.


  Click for Model/Code and Paper
Weighted Clustering Ensemble: A Review

Oct 06, 2019
Mimi Zhang

Clustering ensemble has emerged as a powerful tool for improving both the robustness and the stability of results from individual clustering methods. Weighted clustering ensemble arises naturally from clustering ensemble. One of the arguments for weighted clustering ensemble is that elements (clusterings or clusters) in a clustering ensemble are of different quality, or that objects or features are of varying significance. However, it is not possible to directly apply the weighting mechanisms from classification (supervised) domain to clustering (unsupervised) domain, also because clustering is inherently an ill-posed problem. This paper provides an overview of weighted clustering ensemble by discussing different types of weights, major approaches to determining weight values, and applications of weighted clustering ensemble to complex data. The unifying framework presented in this paper will help clustering practitioners select the most appropriate weighting mechanisms for their own problems.

* Pattern Recognition, 2019 

  Click for Model/Code and Paper
GRESNET: Graph Residuals for Reviving Deep Graph Neural Nets from Suspended Animation

Sep 12, 2019
Jiawei Zhang

In this paper, we will investigate the causes of the GNNs' "suspended animation problem", and analyze if such a problem also exists in all other GNN models or not. GNNs are very different from the traditional deep learning models, and the existing solutions to resolve such problems, e.g., residual terms used in ResNet for CNN, cannot work well for GNNs actually. In this paper, several different novel graph residual terms will be studied for GNNs specially. Equipped with the new graph residual blocks, we will further introduce a new graph neural network architecture, namely graph residual neural network (GRESNET), to resolve the observed problem. Instead of merely stacking the spectral graph convolution layers on each other, GRESNET creates a high-way to allow the raw features of the nodes to be fed into the graph convolution operators in each layer of the model. We will study the effectiveness of the GRESNET architecture and those different graph residuals for several existing vanilla GNNs. In addition, theoretic analyses on GRESNET will be provided in this paper as well to demonstrate its effectiveness from the norm-preservation perspective.

* 10 pages 

  Click for Model/Code and Paper
SeesawFaceNets: sparse and robust face verification model for mobile platform

Aug 27, 2019
Jintao Zhang

Deep Convolutional Neural Network (DCNNs) come to be the most widely used solution for most computer vision related tasks, and one of the most important application scenes is face verification. Due to its high-accuracy performance, deep face verification models of which the inference stage occurs on cloud platform through internet plays the key role on most prectical scenes. However, two critical issues exist: First, individual privacy may not be well protected since they have to upload their personal photo and other private information to the online cloud backend. Secondly, either training or inference stage is time-comsuming and the latency may affect customer experience, especially when the internet link speed is not so stable or in remote areas where mobile reception is not so good, but also in cities where building and other construction may block mobile signals. Therefore, designing lightweight networks with low memory requirement and computational cost is one of the most practical solutions for face verification on mobile platform. In this paper, a novel mobile network named SeesawFaceNets, a simple but effective model, is proposed for productively deploying face recognition for mobile devices. Dense experimental results have shown that our proposed model SeesawFaceNets outperforms the baseline MobilefaceNets, with only {\bf66\%}(146M VS 221M MAdds) computational cost, smaller batch size and less training steps, and SeesawFaceNets achieve comparable performance with other SOTA model e.g. mobiface with only {\bf54.2\%}(1.3M VS 2.4M) parameters and {\bf31.6\%}(146M VS 462M MAdds) computational cost, It is also eventually competitive against large-scale deep-networks face recognition on all 5 listed public validation datasets, with {\bf6.5\%}(4.2M VS 65M) parameters and {\bf4.35\%}(526M VS 12G MAdds) computational cost.

* 8 pages, 2 figures. All source code and proposed models will be released publicly later 

  Click for Model/Code and Paper