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

We developed OmicsMapNet approach to take advantage of existing deep leaning frameworks to analyze high-dimensional omics data as 2-dimensional images. The omics data of individual samples were first rearranged into 2D images in which molecular features related in functions, ontologies, or other relationships were organized in spatially adjacent and patterned locations. Deep learning neural networks were trained to classify the images. Molecular features informative of classes of different phenotypes were subsequently identified. As an example, we used the KEGG BRITE database to rearrange RNA-Seq expression data of TCGA diffuse glioma samples as treemaps to capture the functional hierarchical structure of genes in 2D images. Deep Convolutional Neural Networks (CNN) were derived using tools from TensorFlow to learn the grade of TCGA LGG and GBM samples with relatively high accuracy. The most contributory features in the trained CNN were confirmed in pathway analysis for their plausible functional involvement.

This paper presents a smart sliding Chinese pinyin Input Method Editor (IME) for touchscreen devices which allows user finger sliding from one key to another on the touchscreen instead of tapping keys one by one, while the target Chinese character sequence will be predicted during the sliding process to help user input Chinese characters efficiently. Moreover, the layout of the virtual keyboard of our IME adapts to user sliding for more efficient inputting. The layout adaption process is utilized with Recurrent Neural Networks (RNN) and deep reinforcement learning. The pinyin-to-character converter is implemented with a sequence-to-sequence (Seq2Seq) model to predict the target Chinese sequence. A sliding simulator is built to automatically produce sliding samples for model training and virtual keyboard test. The key advantage of our proposed IME is that nearly all its built-in tactics can be optimized automatically with deep learning algorithms only following user behavior. Empirical studies verify the effectiveness of the proposed model and show a better user input efficiency.

Audio Classical Composer Identification (ACC) is an important problem in Music Information Retrieval (MIR) which aims at identifying the composer for audio classical music clips. The famous annual competition, Music Information Retrieval Evaluation eXchange (MIREX), also takes it as one of the four training&testing tasks. We built a hybrid model based on Deep Belief Network (DBN) and Stacked Denoising Autoencoder (SDA) to identify the composer from audio signal. As a matter of copyright, sponsors of MIREX cannot publish their data set. We built a comparable data set to test our model. We got an accuracy of 76.26% in our data set which is better than some pure models and shallow models. We think our method is promising even though we test it in a different data set, since our data set is comparable to that in MIREX by size. We also found that samples from different classes become farther away from each other when transformed by more layers in our model.

Linguistic large-scale group decision making (LGDM) problems are more and more common nowadays. In such problems a large group of decision makers are involved in the decision process and elicit linguistic information that are usually assessed in different linguistic scales with diverse granularity because of decision makers' distinct knowledge and background. To keep maximum information in initial stages of the linguistic LGDM problems, the use of multi-granular linguistic distribution assessments seems a suitable choice, however to manage such multigranular linguistic distribution assessments, it is necessary the development of a new linguistic computational approach. In this paper it is proposed a novel computational model based on the use of extended linguistic hierarchies, which not only can be used to operate with multi-granular linguistic distribution assessments, but also can provide interpretable linguistic results to decision makers. Based on this new linguistic computational model, an approach to linguistic large-scale multi-attribute group decision making is proposed and applied to a talent selection process in universities.

Removing spatially variant motion blur from a blurry image is a challenging problem as blur sources are complicated and difficult to model accurately. Recent progress in deep neural networks suggests that kernel free single image deblurring can be efficiently performed, but questions about deblurring performance persist. Thus, we propose to restore a sharp image by fusing a pair of noisy/blurry images captured in a burst. Two neural network structures, DeblurRNN and DeblurMerger, are presented to exploit the pair of images in a sequential manner or parallel manner. To boost the training, gradient loss, adversarial loss and spectral normalization are leveraged. The training dataset that consists of pairs of noisy/blurry images and the corresponding ground truth sharp image is synthesized based on the benchmark dataset GOPRO. We evaluated the trained networks on a variety of synthetic datasets and real image pairs. The results demonstrate that the proposed approach outperforms the state-of-the-art both qualitatively and quantitatively.

Most of the successful deep neural network architectures are structured, often consisting of elements like convolutional neural networks and gated recurrent neural networks. Recently, graph neural networks have been successfully applied to graph structured data such as point cloud and molecular data. These networks often only consider pairwise dependencies, as they operate on a graph structure. We generalize the graph neural network into a factor graph neural network (FGNN) in order to capture higher order dependencies. We show that FGNN is able to represent Max-Product Belief Propagation, an approximate inference algorithm on probabilistic graphical models; hence it is able to do well when Max-Product does well. Promising results on both synthetic and real datasets demonstrate the effectiveness of the proposed model.

A conditional general adversarial network (GAN) is proposed for image deblurring problem. It is tailored for image deblurring instead of just applying GAN on the deblurring problem. Motivated by that, dark channel prior is carefully picked to be incorporated into the loss function for network training. To make it more compatible with neuron networks, its original indifferentiable form is discarded and L2 norm is adopted instead. On both synthetic datasets and noisy natural images, the proposed network shows improved deblurring performance and robustness to image noise qualitatively and quantitatively. Additionally, compared to the existing end-to-end deblurring networks, our network structure is light-weight, which ensures less training and testing time.

It is a key to construct a similarity graph in graph-oriented subspace learning and clustering. In a similarity graph, each vertex denotes a data point and the edge weight represents the similarity between two points. There are two popular schemes to construct a similarity graph, i.e., pairwise distance based scheme and linear representation based scheme. Most existing works have only involved one of the above schemes and suffered from some limitations. Specifically, pairwise distance based methods are sensitive to the noises and outliers compared with linear representation based methods. On the other hand, there is the possibility that linear representation based algorithms wrongly select inter-subspaces points to represent a point, which will degrade the performance. In this paper, we propose an algorithm, called Locally Linear Representation (LLR), which integrates pairwise distance with linear representation together to address the problems. The proposed algorithm can automatically encode each data point over a set of points that not only could denote the objective point with less residual error, but also are close to the point in Euclidean space. The experimental results show that our approach is promising in subspace learning and subspace clustering.

We address the problem of Visual Relationship Detection (VRD) which aims to describe the relationships between pairs of objects in the form of triplets of (subject, predicate, object). We observe that given a pair of bounding box proposals, objects often participate in multiple relations implying the distribution of triplets is multimodal. We leverage the strong correlations within triplets to learn the joint distribution of triplet variables conditioned on the image and the bounding box proposals, doing away with the hitherto used independent distribution of triplets. To make learning the triplet joint distribution feasible, we introduce a novel technique of learning conditional triplet distributions in the form of their normalized low rank non-negative tensor decompositions. Normalized tensor decompositions take form of mixture distributions of discrete variables and thus are able to capture multimodality. This allows us to efficiently learn higher order discrete multimodal distributions and at the same time keep the parameter size manageable. We further model the probability of selecting an object proposal pair and include a relation triplet prior in our model. We show that each part of the model improves performance and the combination outperforms state-of-the-art score on the Visual Genome (VG) and Visual Relationship Detection (VRD) datasets.

Modelling and exploiting teammates' policies in cooperative multi-agent systems have long been an interest and also a big challenge for the reinforcement learning (RL) community. The interest lies in the fact that if the agent knows the teammates' policies, it can adjust its own policy accordingly to arrive at proper cooperations; while the challenge is that the agents' policies are changing continuously due to they are learning concurrently, which imposes difficulty to model the dynamic policies of teammates accurately. In this paper, we present \emph{ATTention Multi-Agent Deep Deterministic Policy Gradient} (ATT-MADDPG) to address this challenge. ATT-MADDPG extends DDPG, a single-agent actor-critic RL method, with two special designs. First, in order to model the teammates' policies, the agent should get access to the observations and actions of teammates. ATT-MADDPG adopts a centralized critic to collect such information. Second, to model the teammates' policies using the collected information in an effective way, ATT-MADDPG enhances the centralized critic with an attention mechanism. This attention mechanism introduces a special structure to explicitly model the dynamic joint policy of teammates, making sure that the collected information can be processed efficiently. We evaluate ATT-MADDPG on both benchmark tasks and the real-world packet routing tasks. Experimental results show that it not only outperforms the state-of-the-art RL-based methods and rule-based methods by a large margin, but also achieves better performance in terms of scalability and robustness.

We present an attention based visual analysis framework to compute grasp-relevant information in order to guide grasp planning using a multi-fingered robotic hand. Our approach uses a computational visual attention model to locate regions of interest in a scene, and uses a deep convolutional neural network to detect grasp type and point for a sub-region of the object presented in a region of interest. We demonstrate the proposed framework in object grasping tasks, in which the information generated from the proposed framework is used as prior information to guide the grasp planning. Results show that the proposed framework can not only speed up grasp planning with more stable configurations, but also is able to handle unknown objects. Furthermore, our framework can handle cluttered scenarios. A new Grasp Type Dataset (GTD) that considers 6 commonly used grasp types and covers 12 household objects is also presented.

In this paper, we propose a novel tensor graph convolutional neural network (TGCNN) to conduct convolution on factorizable graphs, for which here two types of problems are focused, one is sequential dynamic graphs and the other is cross-attribute graphs. Especially, we propose a graph preserving layer to memorize salient nodes of those factorized subgraphs, i.e. cross graph convolution and graph pooling. For cross graph convolution, a parameterized Kronecker sum operation is proposed to generate a conjunctive adjacency matrix characterizing the relationship between every pair of nodes across two subgraphs. Taking this operation, then general graph convolution may be efficiently performed followed by the composition of small matrices, which thus reduces high memory and computational burden. Encapsuling sequence graphs into a recursive learning, the dynamics of graphs can be efficiently encoded as well as the spatial layout of graphs. To validate the proposed TGCNN, experiments are conducted on skeleton action datasets as well as matrix completion dataset. The experiment results demonstrate that our method can achieve more competitive performance with the state-of-the-art methods.

Symmetric positive definite (SPD) matrices (e.g., covariances, graph Laplacians, etc.) are widely used to model the relationship of spatial or temporal domain. Nevertheless, SPD matrices are theoretically embedded on Riemannian manifolds. In this paper, we propose an end-to-end deep manifold-to-manifold transforming network (DMT-Net) which can make SPD matrices flow from one Riemannian manifold to another more discriminative one. To learn discriminative SPD features characterizing both spatial and temporal dependencies, we specifically develop three novel layers on manifolds: (i) the local SPD convolutional layer, (ii) the non-linear SPD activation layer, and (iii) the Riemannian-preserved recursive layer. The SPD property is preserved through all layers without any requirement of singular value decomposition (SVD), which is often used in the existing methods with expensive computation cost. Furthermore, a diagonalizing SPD layer is designed to efficiently calculate the final metric for the classification task. To evaluate our proposed method, we conduct extensive experiments on the task of action recognition, where input signals are popularly modeled as SPD matrices. The experimental results demonstrate that our DMT-Net is much more competitive over state-of-the-art.

In this paper, we present a novel deep learning approach, deeply-fused nets. The central idea of our approach is deep fusion, i.e., combine the intermediate representations of base networks, where the fused output serves as the input of the remaining part of each base network, and perform such combinations deeply over several intermediate representations. The resulting deeply fused net enjoys several benefits. First, it is able to learn multi-scale representations as it enjoys the benefits of more base networks, which could form the same fused network, other than the initial group of base networks. Second, in our suggested fused net formed by one deep and one shallow base networks, the flows of the information from the earlier intermediate layer of the deep base network to the output and from the input to the later intermediate layer of the deep base network are both improved. Last, the deep and shallow base networks are jointly learnt and can benefit from each other. More interestingly, the essential depth of a fused net composed from a deep base network and a shallow base network is reduced because the fused net could be composed from a less deep base network, and thus training the fused net is less difficult than training the initial deep base network. Empirical results demonstrate that our approach achieves superior performance over two closely-related methods, ResNet and Highway, and competitive performance compared to the state-of-the-arts.

Recently, deep neural network has shown promising performance in face image recognition. The inputs of most networks are face images, and there is hardly any work reported in literature on network with face videos as input. To sufficiently discover the useful information contained in face videos, we present a novel network architecture called input aggregated network which is able to learn fixed-length representations for variable-length face videos. To accomplish this goal, an aggregation unit is designed to model a face video with various frames as a point on a Riemannian manifold, and the mapping unit aims at mapping the point into high-dimensional space where face videos belonging to the same subject are close-by and others are distant. These two units together with the frame representation unit build an end-to-end learning system which can learn representations of face videos for the specific tasks. Experiments on two public face video datasets demonstrate the effectiveness of the proposed network.

Graph convolutional networks (GCNs) have shown the powerful ability in text structure representation and effectively facilitate the task of text classification. However, challenges still exist in adapting GCN on learning discriminative features from texts due to the main issue of graph variants incurred by the textual complexity and diversity. In this paper, we propose a dual-attention GCN to model the structural information of various texts as well as tackle the graph-invariant problem through embedding two types of attention mechanisms, i.e. the connection-attention and hop-attention, into the classic GCN. To encode various connection patterns between neighbour words, connection-attention adaptively imposes different weights specified to neighbourhoods of each word, which captures the short-term dependencies. On the other hand, the hop-attention applies scaled coefficients to different scopes during the graph diffusion process to make the model learn more about the distribution of context, which captures long-term semantics in an adaptive way. Extensive experiments are conducted on five widely used datasets to evaluate our dual-attention GCN, and the achieved state-of-the-art performance verifies the effectiveness of dual-attention mechanisms.

Physics-informed neural networks (PINNs) encode physical conservation laws and prior physical knowledge into the neural networks, ensuring the correct physics is represented accurately while alleviating the need for supervised learning to a great degree. While effective for relatively short-term time integration, when long time integration of the time-dependent PDEs is sought, the time-space domain may become arbitrarily large and hence training of the neural network may become prohibitively expensive. To this end, we develop a parareal physics-informed neural network (PPINN), hence decomposing a long-time problem into many independent short-time problems supervised by an inexpensive/fast coarse-grained (CG) solver. In particular, the serial CG solver is designed to provide approximate predictions of the solution at discrete times, while initiate many fine PINNs simultaneously to correct the solution iteratively. There is a two-fold benefit from training PINNs with small-data sets rather than working on a large-data set directly, i.e., training of individual PINNs with small-data is much faster, while training the fine PINNs can be readily parallelized. Consequently, compared to the original PINN approach, the proposed PPINN approach may achieve a significant speedup for long-time integration of PDEs, assuming that the CG solver is fast and can provide reasonable predictions of the solution, hence aiding the PPINN solution to converge in just a few iterations. To investigate the PPINN performance on solving time-dependent PDEs, we first apply the PPINN to solve the Burgers equation, and subsequently we apply the PPINN to solve a two-dimensional nonlinear diffusion-reaction equation. Our results demonstrate that PPINNs converge in a couple of iterations with significant speed-ups proportional to the number of time-subdomains employed.

Face detection has achieved significant progress in recent years. However, high performance face detection still remains a very challenging problem, especially when there exists many tiny faces. In this paper, we present a single-shot refinement face detector namely RefineFace to achieve high performance. Specifically, it consists of five modules: Selective Two-step Regression (STR), Selective Two-step Classification (STC), Scale-aware Margin Loss (SML), Feature Supervision Module (FSM) and Receptive Field Enhancement (RFE). To enhance the regression ability for high location accuracy, STR coarsely adjusts locations and sizes of anchors from high level detection layers to provide better initialization for subsequent regressor. To improve the classification ability for high recall efficiency, STC first filters out most simple negatives from low level detection layers to reduce search space for subsequent classifier, then SML is applied to better distinguish faces from background at various scales and FSM is introduced to let the backbone learn more discriminative features for classification. Besides, RFE is presented to provide more diverse receptive field to better capture faces in some extreme poses. Extensive experiments conducted on WIDER FACE, AFW, PASCAL Face, FDDB, MAFA demonstrate that our method achieves state-of-the-art results and runs at $37.3$ FPS with ResNet-18 for VGA-resolution images.