Chao Li

is this you? claim profile


Assistant professor, School of civil and environmental engineering, Harbin Institute of Technology Shenzhen Graduate School

  • Semantic Adversarial Network with Multi-scale Pyramid Attention for Video Classification

    Two-stream architecture have shown strong performance in video classification task. The key idea is to learn spatio-temporal features by fusing convolutional networks spatially and temporally. However, there are some problems within such architecture. First, it relies on optical flow to model temporal information, which are often expensive to compute and store. Second, it has limited ability to capture details and local context information for video data. Third, it lacks explicit semantic guidance that greatly decrease the classification performance. In this paper, we proposed a new two-stream based deep framework for video classification to discover spatial and temporal information only from RGB frames, moreover, the multi-scale pyramid attention (MPA) layer and the semantic adversarial learning (SAL) module is introduced and integrated in our framework. The MPA enables the network capturing global and local feature to generate a comprehensive representation for video, and the SAL can make this representation gradually approximate to the real video semantics in an adversarial manner. Experimental results on two public benchmarks demonstrate our proposed methods achieves state-of-the-art results on standard video datasets.

    03/06/2019 ∙ by De Xie, et al. ∙ 16 share

    read it

  • Active Transfer Learning Network: A Unified Deep Joint Spectral-Spatial Feature Learning Model For Hyperspectral Image Classification

    Deep learning has recently attracted significant attention in the field of hyperspectral images (HSIs) classification. However, the construction of an efficient deep neural network (DNN) mostly relies on a large number of labeled samples being available. To address this problem, this paper proposes a unified deep network, combined with active transfer learning that can be well-trained for HSIs classification using only minimally labeled training data. More specifically, deep joint spectral-spatial feature is first extracted through hierarchical stacked sparse autoencoder (SSAE) networks. Active transfer learning is then exploited to transfer the pre-trained SSAE network and the limited training samples from the source domain to the target domain, where the SSAE network is subsequently fine-tuned using the limited labeled samples selected from both source and target domain by corresponding active learning strategies. The advantages of our proposed method are threefold: 1) the network can be effectively trained using only limited labeled samples with the help of novel active learning strategies; 2) the network is flexible and scalable enough to function across various transfer situations, including cross-dataset and intra-image; 3) the learned deep joint spectral-spatial feature representation is more generic and robust than many joint spectral-spatial feature representation. Extensive comparative evaluations demonstrate that our proposed method significantly outperforms many state-of-the-art approaches, including both traditional and deep network-based methods, on three popular datasets.

    04/04/2019 ∙ by Cheng Deng, et al. ∙ 10 share

    read it

  • Non-local Meets Global: An Integrated Paradigm for Hyperspectral Denoising

    Non-local low-rank tensor approximation has been developed as a state-of-the-art method for hyperspectral image (HSI) denoising. Unfortunately, with more spectral bands for HSI, while the running time of these methods significantly increases, their denoising performance benefits little. In this paper, we claim that the HSI underlines a global spectral low-rank subspace, and the spectral subspaces of each full band patch groups should underlie this global low-rank subspace. This motivates us to propose a unified spatial-spectral paradigm for HSI denoising. As the new model is hard to optimize, we further propose an efficient algorithm for optimization, which is motivated by alternating minimization. This is done by first learning a low-dimensional projection and the related reduced image from the noisy HSI. Then, the non-local low-rank denoising and iterative regularization are developed to refine the reduced image and projection, respectively. Finally, experiments on synthetic and both real datasets demonstrate the superiority against the other state-of-the-arts HSI denoising methods.

    12/11/2018 ∙ by Wei He, et al. ∙ 6 share

    read it

  • A generative adversarial framework for positive-unlabeled classification

    In this work, we consider the task of classifying the binary positive-unlabeled (PU) data. The existing discriminative learning based PU models attempt to seek an optimal re-weighting strategy for U data, so that a decent decision boundary can be found. In contrast, we provide a totally new paradigm to attack the binary PU task, from perspective of generative learning by leveraging the powerful generative adversarial networks (GANs). Our generative positive-unlabeled (GPU) learning model is devised to express P and N data distributions. It comprises of three discriminators and two generators with different roles, producing both positive and negative samples that resemble those come from the real training dataset. Even with rather limited labeled P data, our GPU framework is capable of capturing the underlying P and N data distribution with infinite realistic sample streams. In this way, an optimal classifier can be trained on those generated samples using a very deep neural networks (DNNs). Moreover, an useful variant of GPU is also introduced for semi-supervised classification.

    11/21/2017 ∙ by Ming Hou, et al. ∙ 0 share

    read it

  • Autoencoder Feature Selector

    High-dimensional data in many areas such as computer vision and machine learning brings in computational and analytical difficulty. Feature selection which select a subset of features from original ones has been proven to be effective and efficient to deal with high-dimensional data. In this paper, we propose a novel AutoEncoder Feature Selector (AEFS) for unsupervised feature selection. AEFS is based on the autoencoder and the group lasso regularization. Compared to traditional feature selection methods, AEFS can select the most important features in spite of nonlinear and complex correlation among features. It can be viewed as a nonlinear extension of the linear method regularized self-representation (RSR) for unsupervised feature selection. In order to deal with noise and corruption, we also propose robust AEFS. An efficient iterative algorithm is designed for model optimization and experimental results verify the effectiveness and superiority of the proposed method.

    10/23/2017 ∙ by Kai Han, et al. ∙ 0 share

    read it

  • Cascade Region Proposal and Global Context for Deep Object Detection

    Deep region-based object detector consists of a region proposal step and a deep object recognition step. In this paper, we make significant improvements on both of the two steps. For region proposal we propose a novel lightweight cascade structure which can effectively improve RPN proposal quality. For object recognition we re-implement global context modeling with a few modications and obtain a performance boost (4.2 validation set). Besides, we apply the idea of pre-training extensively and show its importance in both steps. Together with common training and testing tricks, we improve Faster R-CNN baseline by a large margin. In particular, we obtain 87.9 set and 36.8

    10/30/2017 ∙ by Qiaoyong Zhong, et al. ∙ 0 share

    read it

  • Canonical Polyadic Decomposition with Auxiliary Information for Brain Computer Interface

    Physiological signals are often organized in the form of multiple dimensions (e.g., channel, time, task, and 3D voxel), so it is better to preserve original organization structure when processing. Unlike vector-based methods that destroy data structure, Canonical Polyadic Decomposition (CPD) aims to process physiological signals in the form of multi-way array, which considers relationships between dimensions and preserves structure information contained by the physiological signal. Nowadays, CPD is utilized as an unsupervised method for feature extraction in a classification problem. After that, a classifier, such as support vector machine, is required to classify those features. In this manner, classification task is achieved in two isolated steps. We proposed supervised Canonical Polyadic Decomposition by directly incorporating auxiliary label information during decomposition, by which a classification task can be achieved without an extra step of classifier training. The proposed method merges the decomposition and classifier learning together, so it reduces procedure of classification task compared with that of respective decomposition and classification. In order to evaluate the performance of the proposed method, three different kinds of signals, synthetic signal, EEG signal, and MEG signal, were used. The results based on evaluations of synthetic and real signals demonstrated that the proposed method is effective and efficient.

    10/23/2014 ∙ by Junhua Li, et al. ∙ 0 share

    read it

  • Multi-tensor Completion for Estimating Missing Values in Video Data

    Many tensor-based data completion methods aim to solve image and video in-painting problems. But, all methods were only developed for a single dataset. In most of real applications, we can usually obtain more than one dataset to reflect one phenomenon, and all the datasets are mutually related in some sense. Thus one question raised whether such the relationship can improve the performance of data completion or not? In the paper, we proposed a novel and efficient method by exploiting the relationship among datasets for multi-video data completion. Numerical results show that the proposed method significantly improve the performance of video in-painting, particularly in the case of very high missing percentage.

    09/01/2014 ∙ by Chao Li, et al. ∙ 0 share

    read it

  • Deep Speaker: an End-to-End Neural Speaker Embedding System

    We present Deep Speaker, a neural speaker embedding system that maps utterances to a hypersphere where speaker similarity is measured by cosine similarity. The embeddings generated by Deep Speaker can be used for many tasks, including speaker identification, verification, and clustering. We experiment with ResCNN and GRU architectures to extract the acoustic features, then mean pool to produce utterance-level speaker embeddings, and train using triplet loss based on cosine similarity. Experiments on three distinct datasets suggest that Deep Speaker outperforms a DNN-based i-vector baseline. For example, Deep Speaker reduces the verification equal error rate by 50 (relatively) and improves the identification accuracy by 60 text-independent dataset. We also present results that suggest adapting from a model trained with Mandarin can improve accuracy for English speaker recognition.

    05/05/2017 ∙ by Chao Li, et al. ∙ 0 share

    read it

  • Model Trees for Identifying Exceptional Players in the NHL Draft

    Drafting strong players is crucial for the team success. We describe a new data-driven interpretable approach for assessing draft prospects in the National Hockey League. Successful previous approaches have built a predictive model based on player features, or derived performance predictions from the observed performance of comparable players in a cohort. This paper develops model tree learning, which incorporates strengths of both model-based and cohort-based approaches. A model tree partitions the feature space according to the values of discrete features, or learned thresholds for continuous features. Each leaf node in the tree defines a group of players, easily described to hockey experts, with its own group regression model. Compared to a single model, the model tree forms an ensemble that increases predictive power. Compared to cohort-based approaches, the groups of comparables are discovered from the data, without requiring a similarity metric. The performance predictions of the model tree are competitive with the state-of-the-art methods, which validates our model empirically. We show in case studies that the model tree player ranking can be used to highlight strong and weak points of players.

    02/23/2018 ∙ by Oliver Schulte, et al. ∙ 0 share

    read it

  • Combining Linear Non-Gaussian Acyclic Model with Logistic Regression Model for Estimating Causal Structure from Mixed Continuous and Discrete Data

    Estimating causal models from observational data is a crucial task in data analysis. For continuous-valued data, Shimizu et al. have proposed a linear acyclic non-Gaussian model to understand the data generating process, and have shown that their model is identifiable when the number of data is sufficiently large. However, situations in which continuous and discrete variables coexist in the same problem are common in practice. Most existing causal discovery methods either ignore the discrete data and apply a continuous-valued algorithm or discretize all the continuous data and then apply a discrete Bayesian network approach. These methods possibly loss important information when we ignore discrete data or introduce the approximation error due to discretization. In this paper, we define a novel hybrid causal model which consists of both continuous and discrete variables. The model assumes: (1) the value of a continuous variable is a linear function of its parent variables plus a non-Gaussian noise, and (2) each discrete variable is a logistic variable whose distribution parameters depend on the values of its parent variables. In addition, we derive the BIC scoring function for model selection. The new discovery algorithm can learn causal structures from mixed continuous and discrete data without discretization. We empirically demonstrate the power of our method through thorough simulations.

    02/16/2018 ∙ by Chao Li, et al. ∙ 0 share

    read it