Models, code, and papers for "Geng Zhan":

FIS-GAN: GAN with Flow-based Importance Sampling

Oct 06, 2019
Shiyu Yi, Donglin Zhan, Zhengyang Geng, Wenqing Zhang, Chang Xu

Generative Adversarial Networks (GAN) training process, in most cases, apply uniform and Gaussian sampling methods in latent space, which probably spends most of the computation on examples that can be properly handled and easy to generate. Theoretically, importance sampling speeds up stochastic gradient algorithms for supervised learning by prioritizing training examples. In this paper, we explore the possibility for adapting importance sampling into adversarial learning. We use importance sampling to replace uniform and Gaussian sampling methods in latent space and combine normalizing flow with importance sampling to approximate latent space posterior distribution by density estimation. Empirically, results on MNIST and Fashion-MNIST demonstrate that our method significantly accelerates the convergence of generative process while retaining visual fidelity in generated samples.

* 10 pages, 9 figures, another format submitted to AAAI-2020, under review. arXiv admin note: text overlap with arXiv:1803.00942 by other authors 

  Click for Model/Code and Paper
ACFM: A Dynamic Spatial-Temporal Network for Traffic Prediction

Sep 02, 2019
Lingbo Liu, Jiajie Zhen, Guanbin Li, Geng Zhan, Liang Lin

As a crucial component in intelligent transportation systems, crowd flow prediction has recently attracted widespread research interest in the field of artificial intelligence (AI) with the increasing availability of large-scale traffic mobility data. Its key challenge lies in how to integrate diverse factors (such as temporal laws and spatial dependencies) to infer the evolution trend of crowd flow. To address this problem, we propose a unified neural network called Attentive Crowd Flow Machine (ACFM), which can effectively learn the spatial-temporal feature representations of crowd flow with an attention mechanism. In particular, our ACFM is composed of two progressive ConvLSTM units connected with a convolutional layer. Specifically, the first LSTM unit takes normal crowd flow features as input and generates a hidden state at each time-step, which is further fed into the connected convolutional layer for spatial attention map inference. The second LSTM unit aims at learning the dynamic spatial-temporal representations from the attentionally weighted crowd flow features. Further, we develop two deep frameworks based on ACFM to predict citywide short-term/long-term crowd flow by adaptively incorporating the sequential and periodic data as well as other external influences. Extensive experiments on two standard benchmarks well demonstrate the superiority of the proposed method for crowd flow prediction. Moreover, to verify the generalization of our method, we also apply the customized framework to forecast the passenger pickup/dropoff demands and show its superior performance in this traffic prediction task.

* arXiv admin note: substantial text overlap with arXiv:1809.00101 

  Click for Model/Code and Paper
Extended Local Binary Patterns for Efficient and Robust Spontaneous Facial Micro-Expression Recognition

Jul 22, 2019
Chengyu Guo, Jingyun Liang, Geng Zhan, Zhong Liu, Matti Pietikäinen, Li Liu

Facial MicroExpressions (MEs) are spontaneous, involuntary facial movements when a person experiences an emotion but deliberately or unconsciously attempts to conceal his or her genuine emotions. Recently, ME recognition has attracted increasing attention due to its potential applications such as clinical diagnosis, business negotiation, interrogations and security. However, it is expensive to build large scale ME datasets, mainly due to the difficulty of naturally inducing spontaneous MEs. This limits the application of deep learning techniques which require lots of training data. In this paper, we propose a simple, efficient yet robust descriptor called Extended Local Binary Patterns on Three Orthogonal Planes (ELBPTOP) for ME recognition. ELBPTOP consists of three complementary binary descriptors: LBPTOP and two novel ones Radial Difference LBPTOP (RDLBPTOP) and Angular Difference LBPTOP (ADLBPTOP), which explore the local second order information along radial and angular directions contained in ME video sequences. ELBPTOP is a novel ME descriptor inspired by the unique and subtle facial movements. It is computationally efficient and only marginally increases the cost of computing LBPTOP, yet is extremely effective for ME recognition. In addition, by firstly introducing Whitened Principal Component Analysis (WPCA) to ME recognition, we can further obtain more compact and discriminative feature representations, and achieve significantly computational savings. Extensive experimental evaluation on three popular spontaneous ME datasets SMIC, CASMEII and SAMM show that our proposed ELBPTOP approach significantly outperforms previous state of the art on all three evaluated datasets. Our proposed ELBPTOP achieves 73.94% on CASMEII, which is 6.6% higher than state of the art on this dataset. More impressively, ELBPTOP increases recognition accuracy from 44.7% to 63.44% on the SAMM dataset.

  Click for Model/Code and Paper
Evolutionary method for finding communities in bipartite networks

Jun 04, 2011
Zhan WeiHua, Zhang Zhongzhi, Guan Jihong, Zhou Shuigeng

An important step in unveiling the relation between network structure and dynamics defined on networks is to detect communities, and numerous methods have been developed separately to identify community structure in different classes of networks, such as unipartite networks, bipartite networks, and directed networks. We show that both unipartite and directed networks can be represented as bipartite networks, and their modularity is completely consistent with that for bipartite networks, the detection of modular structure on which can be reformulated as modularity maximization. To optimize the bipartite modularity, we develop a modified adaptive genetic algorithm (MAGA), which is shown to be especially efficient for community structure detection. The high efficiency of the MAGA is based on the following three improvements we make. First, we introduce a different measure for the informativeness of a locus instead of the standard deviation, which can exactly determine which loci mutate. This measure is the bias between the distribution of a locus over the current population and the uniform distribution of the locus, i.e., the Kullback-Leibler divergence between them. Second, we develop a reassignment technique for differentiating the informative state a locus has attained from the random state in the initial phase. Third, we present a modified mutation rule which by incorporating related operation can guarantee the convergence of the MAGA to the global optimum and can speed up the convergence process. Experimental results show that the MAGA outperforms existing methods in terms of modularity for both bipartite and unipartite networks.

* 15 pages, 9 figures 

  Click for Model/Code and Paper
2nd Place Solution to the GQA Challenge 2019

Aug 16, 2019
Shijie Geng, Ji Zhang, Hang Zhang, Ahmed Elgammal, Dimitris N. Metaxas

We present a simple method that achieves unexpectedly superior performance for Complex Reasoning involved Visual Question Answering. Our solution collects statistical features from high-frequency words of all the questions asked about an image and use them as accurate knowledge for answering further questions of the same image. We are fully aware that this setting is not ubiquitously applicable, and in a more common setting one should assume the questions are asked separately and they cannot be gathered to obtain a knowledge base. Nonetheless, we use this method as an evidence to demonstrate our observation that the bottleneck effect is more severe on the feature extraction part than it is on the knowledge reasoning part. We show significant gaps when using the same reasoning model with 1) ground-truth features; 2) statistical features; 3) detected features from completely learned detectors, and analyze what these gaps mean to researches on visual reasoning topics. Our model with the statistical features achieves the 2nd place in the GQA Challenge 2019.

  Click for Model/Code and Paper
Learning data augmentation policies using augmented random search

Nov 12, 2018
Mingyang Geng, Kele Xu, Bo Ding, Huaimin Wang, Lei Zhang

Previous attempts for data augmentation are designed manually, and the augmentation policies are dataset-specific. Recently, an automatic data augmentation approach, named AutoAugment, is proposed using reinforcement learning. AutoAugment searches for the augmentation polices in the discrete search space, which may lead to a sub-optimal solution. In this paper, we employ the Augmented Random Search method (ARS) to improve the performance of AutoAugment. Our key contribution is to change the discrete search space to continuous space, which will improve the searching performance and maintain the diversities between sub-policies. With the proposed method, state-of-the-art accuracies are achieved on CIFAR-10, CIFAR-100, and ImageNet (without additional data). Our code is available at

* Submitted to ICASSP 

  Click for Model/Code and Paper
Design, Modeling and Control of A Novel Amphibious Robot with Dual-swing-legs Propulsion Mechanism

Sep 21, 2015
Yang Yi, Zhou Geng, Zhang Jianqing, Cheng Siyuan, Fu Mengyin

This paper describes a novel amphibious robot, which adopts a dual-swing-legs propulsion mechanism, proposing a new locomotion mode. The robot is called FroBot, since its structure and locomotion are similar to frogs. Our inspiration comes from the frog scooter and breaststroke. Based on its swing leg mechanism, an unusual universal wheel structure is used to generate propulsion on land, while a pair of flexible caudal fins functions like the foot flippers of a frog to generate similar propulsion underwater. On the basis of the prototype design and the dynamic model of the robot, some locomotion control simulations and experiments were conducted for the purpose of adjusting the parameters that affect the propulsion of the robot. Finally, a series of underwater experiments were performed to verify the design feasibility of FroBot and the rationality of the control algorithm.

* 8 pages 

  Click for Model/Code and Paper
Unsupervised Learning-based Depth Estimation aided Visual SLAM Approach

Jan 22, 2019
Mingyang Geng, Suning Shang, Bo Ding, Huaimin Wang, Pengfei Zhang, Lei Zhang

The RGB-D camera maintains a limited range for working and is hard to accurately measure the depth information in a far distance. Besides, the RGB-D camera will easily be influenced by strong lighting and other external factors, which will lead to a poor accuracy on the acquired environmental depth information. Recently, deep learning technologies have achieved great success in the visual SLAM area, which can directly learn high-level features from the visual inputs and improve the estimation accuracy of the depth information. Therefore, deep learning technologies maintain the potential to extend the source of the depth information and improve the performance of the SLAM system. However, the existing deep learning-based methods are mainly supervised and require a large amount of ground-truth depth data, which is hard to acquire because of the realistic constraints. In this paper, we first present an unsupervised learning framework, which not only uses image reconstruction for supervising but also exploits the pose estimation method to enhance the supervised signal and add training constraints for the task of monocular depth and camera motion estimation. Furthermore, we successfully exploit our unsupervised learning framework to assist the traditional ORB-SLAM system when the initialization module of ORB-SLAM method could not match enough features. Qualitative and quantitative experiments have shown that our unsupervised learning framework performs the depth estimation task comparable to the supervised methods and outperforms the previous state-of-the-art approach by $13.5\%$ on KITTI dataset. Besides, our unsupervised learning framework could significantly accelerate the initialization process of ORB-SLAM system and effectively improve the accuracy on environmental mapping in strong lighting and weak texture scenes.

* 27 pages 

  Click for Model/Code and Paper
Stochastic Conjugate Gradient Algorithm with Variance Reduction

Oct 16, 2018
Xiao-Bo Jin, Xu-Yao Zhang, Kaizhu Huang, Guang-Gang Geng

Conjugate gradient (CG) methods are a class of important methods for solving linear equations and nonlinear optimization problems. In this paper, we propose a new stochastic CG algorithm with variance reduction and we prove its linear convergence with the Fletcher and Reeves method for strongly convex and smooth functions. We experimentally demonstrate that the CG with variance reduction algorithm converges faster than its counterparts for four learning models, which may be convex, nonconvex or nonsmooth. In addition, its area under the curve performance on six large-scale data sets is comparable to that of the LIBLINEAR solver for the L2-regularized L2-loss but with a significant improvement in computational efficiency

* IEEE Transactions on Neural Networks and Learning Systems,2018 
* 10 pages, 4 figures, appeared in IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, CGVR algorithm is available on github: 

  Click for Model/Code and Paper
Multi-Modal Graph Interaction for Multi-Graph Convolution Network in Urban Spatiotemporal Forecasting

May 27, 2019
Xu Geng, Xiyu Wu, Lingyu Zhang, Qiang Yang, Yan Liu, Jieping Ye

Graph convolution network based approaches have been recently used to model region-wise relationships in region-level prediction problems in urban computing. Each relationship represents a kind of spatial dependency, like region-wise distance or functional similarity. To incorporate multiple relationships into spatial feature extraction, we define the problem as a multi-modal machine learning problem on multi-graph convolution networks. Leveraging the advantage of multi-modal machine learning, we propose to develop modality interaction mechanisms for this problem, in order to reduce generalization error by reinforcing the learning of multimodal coordinated representations. In this work, we propose two interaction techniques for handling features in lower layers and higher layers respectively. In lower layers, we propose grouped GCN to combine the graph connectivity from different modalities for more complete spatial feature extraction. In higher layers, we adapt multi-linear relationship networks to GCN by exploring the dimension transformation and freezing part of the covariance structure. The adapted approach, called multi-linear relationship GCN, learns more generalized features to overcome the train-test divergence induced by time shifting. We evaluated our model on ridehailing demand forecasting problem using two real-world datasets. The proposed technique outperforms state-of-the art baselines in terms of prediction accuracy, training efficiency, interpretability and model robustness.

  Click for Model/Code and Paper
Meta-GNN: On Few-shot Node Classification in Graph Meta-learning

May 23, 2019
Fan Zhou, Chengtai Cao, Kunpeng Zhang, Goce Trajcevski, Ting Zhong, Ji Geng

Meta-learning has received a tremendous recent attention as a possible approach for mimicking human intelligence, i.e., acquiring new knowledge and skills with little or even no demonstration. Most of the existing meta-learning methods are proposed to tackle few-shot learning problems such as image and text, in rather Euclidean domain. However, there are very few works applying meta-learning to non-Euclidean domains, and the recently proposed graph neural networks (GNNs) models do not perform effectively on graph few-shot learning problems. Towards this, we propose a novel graph meta-learning framework -- Meta-GNN -- to tackle the few-shot node classification problem in graph meta-learning settings. It obtains the prior knowledge of classifiers by training on many similar few-shot learning tasks and then classifies the nodes from new classes with only few labeled samples. Additionally, Meta-GNN is a general model that can be straightforwardly incorporated into any existing state-of-the-art GNN. Our experiments conducted on three benchmark datasets demonstrate that our proposed approach not only improves the node classification performance by a large margin on few-shot learning problems in meta-learning paradigm, but also learns a more general and flexible model for task adaption.

  Click for Model/Code and Paper
Improving Device-Edge Cooperative Inference of Deep Learning via 2-Step Pruning

Mar 08, 2019
Wenqi Shi, Yunzhong Hou, Sheng Zhou, Zhisheng Niu, Yang Zhang, Lu Geng

Deep neural networks (DNNs) are state-of-the-art solutions for many machine learning applications, and have been widely used on mobile devices. Running DNNs on resource-constrained mobile devices often requires the help from edge servers via computation offloading. However, offloading through a bandwidth-limited wireless link is non-trivial due to the tight interplay between the computation resources on mobile devices and wireless resources. Existing studies have focused on cooperative inference where DNN models are partitioned at different neural network layers, and the two parts are executed at the mobile device and the edge server, respectively. Since the output data size of a DNN layer can be larger than that of the raw data, offloading intermediate data between layers can suffer from high transmission latency under limited wireless bandwidth. In this paper, we propose an efficient and flexible 2-step pruning framework for DNN partition between mobile devices and edge servers. In our framework, the DNN model only needs to be pruned once in the training phase where unimportant convolutional filters are removed iteratively. By limiting the pruning region, our framework can greatly reduce either the wireless transmission workload of the device or the total computation workload. A series of pruned models are generated in the training phase, from which the framework can automatically select to satisfy varying latency and accuracy requirements. Furthermore, coding for the intermediate data is added to provide extra transmission workload reduction. Our experiments show that the proposed framework can achieve up to 25.6$\times$ reduction on transmission workload, 6.01$\times$ acceleration on total computation and 4.81$\times$ reduction on end-to-end latency as compared to partitioning the original DNN model without pruning.

  Click for Model/Code and Paper
Quantized Densely Connected U-Nets for Efficient Landmark Localization

Aug 10, 2018
Zhiqiang Tang, Xi Peng, Shijie Geng, Lingfei Wu, Shaoting Zhang, Dimitris Metaxas

In this paper, we propose quantized densely connected U-Nets for efficient visual landmark localization. The idea is that features of the same semantic meanings are globally reused across the stacked U-Nets. This dense connectivity largely improves the information flow, yielding improved localization accuracy. However, a vanilla dense design would suffer from critical efficiency issue in both training and testing. To solve this problem, we first propose order-K dense connectivity to trim off long-distance shortcuts; then, we use a memory-efficient implementation to significantly boost the training efficiency and investigate an iterative refinement that may slice the model size in half. Finally, to reduce the memory consumption and high precision operations both in training and testing, we further quantize weights, inputs, and gradients of our localization network to low bit-width numbers. We validate our approach in two tasks: human pose estimation and face alignment. The results show that our approach achieves state-of-the-art localization accuracy, but using ~70% fewer parameters, ~98% less model size and saving ~75% training memory compared with other benchmark localizers. The code is available at

* ECCV2018 

  Click for Model/Code and Paper
Character Distributions of Classical Chinese Literary Texts: Zipf's Law, Genres, and Epochs

Sep 17, 2017
Chao-Lin Liu, Shuhua Zhang, Yuanli Geng, Huei-ling Lai, Hongsu Wang

We collect 14 representative corpora for major periods in Chinese history in this study. These corpora include poetic works produced in several dynasties, novels of the Ming and Qing dynasties, and essays and news reports written in modern Chinese. The time span of these corpora ranges between 1046 BCE and 2007 CE. We analyze their character and word distributions from the viewpoint of the Zipf's law, and look for factors that affect the deviations and similarities between their Zipfian curves. Genres and epochs demonstrated their influences in our analyses. Specifically, the character distributions for poetic works of between 618 CE and 1644 CE exhibit striking similarity. In addition, although texts of the same dynasty may tend to use the same set of characters, their character distributions still deviate from each other.

* 12 pages, 2 tables, 6 figures, 2017 International Conference on Digital Humanities 

  Click for Model/Code and Paper
Ridesourcing Car Detection by Transfer Learning

May 23, 2017
Leye Wang, Xu Geng, Jintao Ke, Chen Peng, Xiaojuan Ma, Daqing Zhang, Qiang Yang

Ridesourcing platforms like Uber and Didi are getting more and more popular around the world. However, unauthorized ridesourcing activities taking advantages of the sharing economy can greatly impair the healthy development of this emerging industry. As the first step to regulate on-demand ride services and eliminate black market, we design a method to detect ridesourcing cars from a pool of cars based on their trajectories. Since licensed ridesourcing car traces are not openly available and may be completely missing in some cities due to legal issues, we turn to transferring knowledge from public transport open data, i.e, taxis and buses, to ridesourcing detection among ordinary vehicles. We propose a two-stage transfer learning framework. In Stage 1, we take taxi and bus data as input to learn a random forest (RF) classifier using trajectory features shared by taxis/buses and ridesourcing/other cars. Then, we use the RF to label all the candidate cars. In Stage 2, leveraging the subset of high confident labels from the previous stage as input, we further learn a convolutional neural network (CNN) classifier for ridesourcing detection, and iteratively refine RF and CNN, as well as the feature set, via a co-training process. Finally, we use the resulting ensemble of RF and CNN to identify the ridesourcing cars in the candidate pool. Experiments on real car, taxi and bus traces show that our transfer learning framework, with no need of a pre-labeled ridesourcing dataset, can achieve similar accuracy as the supervised learning methods.

  Click for Model/Code and Paper
An Area and Energy Efficient Design of Domain-Wall Memory-Based Deep Convolutional Neural Networks using Stochastic Computing

Feb 03, 2018
Xiaolong Ma, Yipeng Zhang, Geng Yuan, Ao Ren, Zhe Li, Jie Han, Jingtong Hu, Yanzhi Wang

With recent trend of wearable devices and Internet of Things (IoTs), it becomes attractive to develop hardware-based deep convolutional neural networks (DCNNs) for embedded applications, which require low power/energy consumptions and small hardware footprints. Recent works demonstrated that the Stochastic Computing (SC) technique can radically simplify the hardware implementation of arithmetic units and has the potential to satisfy the stringent power requirements in embedded devices. However, in these works, the memory design optimization is neglected for weight storage, which will inevitably result in large hardware cost. Moreover, if conventional volatile SRAM or DRAM cells are utilized for weight storage, the weights need to be re-initialized whenever the DCNN platform is re-started. In order to overcome these limitations, in this work we adopt an emerging non-volatile Domain-Wall Memory (DWM), which can achieve ultra-high density, to replace SRAM for weight storage in SC-based DCNNs. We propose DW-CNN, the first comprehensive design optimization framework of DWM-based weight storage method. We derive the optimal memory type, precision, and organization, as well as whether to store binary or stochastic numbers. We present effective resource sharing scheme for DWM-based weight storage in the convolutional and fully-connected layers of SC-based DCNNs to achieve a desirable balance among area, power (energy) consumption, and application-level accuracy.

  Click for Model/Code and Paper
Real-Time User-Guided Image Colorization with Learned Deep Priors

May 08, 2017
Richard Zhang, Jun-Yan Zhu, Phillip Isola, Xinyang Geng, Angela S. Lin, Tianhe Yu, Alexei A. Efros

We propose a deep learning approach for user-guided image colorization. The system directly maps a grayscale image, along with sparse, local user "hints" to an output colorization with a Convolutional Neural Network (CNN). Rather than using hand-defined rules, the network propagates user edits by fusing low-level cues along with high-level semantic information, learned from large-scale data. We train on a million images, with simulated user inputs. To guide the user towards efficient input selection, the system recommends likely colors based on the input image and current user inputs. The colorization is performed in a single feed-forward pass, enabling real-time use. Even with randomly simulated user inputs, we show that the proposed system helps novice users quickly create realistic colorizations, and offers large improvements in colorization quality with just a minute of use. In addition, we demonstrate that the framework can incorporate other user "hints" to the desired colorization, showing an application to color histogram transfer. Our code and models are available at

* Accepted to SIGGRAPH 2017. Project page: 

  Click for Model/Code and Paper
Deep Reinforcement Learning for Tensegrity Robot Locomotion

Mar 08, 2017
Marvin Zhang, Xinyang Geng, Jonathan Bruce, Ken Caluwaerts, Massimo Vespignani, Vytas SunSpiral, Pieter Abbeel, Sergey Levine

Tensegrity robots, composed of rigid rods connected by elastic cables, have a number of unique properties that make them appealing for use as planetary exploration rovers. However, control of tensegrity robots remains a difficult problem due to their unusual structures and complex dynamics. In this work, we show how locomotion gaits can be learned automatically using a novel extension of mirror descent guided policy search (MDGPS) applied to periodic locomotion movements, and we demonstrate the effectiveness of our approach on tensegrity robot locomotion. We evaluate our method with real-world and simulated experiments on the SUPERball tensegrity robot, showing that the learned policies generalize to changes in system parameters, unreliable sensor measurements, and variation in environmental conditions, including varied terrains and a range of different gravities. Our experiments demonstrate that our method not only learns fast, power-efficient feedback policies for rolling gaits, but that these policies can succeed with only the limited onboard sensing provided by SUPERball's accelerometers. We compare the learned feedback policies to learned open-loop policies and hand-engineered controllers, and demonstrate that the learned policy enables the first continuous, reliable locomotion gait for the real SUPERball robot. Our code and other supplementary materials are available from

* International Conference on Robotics and Automation (ICRA), 2017. Project website link is 

  Click for Model/Code and Paper
Aesthetic Attributes Assessment of Images

Jul 29, 2019
Xin Jin, Le Wu, Geng Zhao, Xiaodong Li, Xiaokun Zhang, Shiming Ge, Dongqing Zou, Bin Zhou, Xinghui Zhou

Image aesthetic quality assessment has been a relatively hot topic during the last decade. Most recently, comments type assessment (aesthetic captions) has been proposed to describe the general aesthetic impression of an image using text. In this paper, we propose Aesthetic Attributes Assessment of Images, which means the aesthetic attributes captioning. This is a new formula of image aesthetic assessment, which predicts aesthetic attributes captions together with the aesthetic score of each attribute. We introduce a new dataset named \emph{DPC-Captions} which contains comments of up to 5 aesthetic attributes of one image through knowledge transfer from a full-annotated small-scale dataset. Then, we propose Aesthetic Multi-Attribute Network (AMAN), which is trained on a mixture of fully-annotated small-scale PCCD dataset and weakly-annotated large-scale DPC-Captions dataset. Our AMAN makes full use of transfer learning and attention model in a single framework. The experimental results on our DPC-Captions and PCCD dataset reveal that our method can predict captions of 5 aesthetic attributes together with numerical score assessment of each attribute. We use the evaluation criteria used in image captions to prove that our specially designed AMAN model outperforms traditional CNN-LSTM model and modern SCA-CNN model of image captions.

* to appear in ACM MM 2019, camera ready version 

  Click for Model/Code and Paper