Cheng Wu

Cheng Wu

Auto-generated profile, based on publicly available information

Cheng Wu

Department of Automation, Tsinghua University, Beijing, China

Research Focus & Metrics

Academic Career Length

28Years (1999-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 January 2021 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
YWYulin Wang
Yulin Wang
GHGao Huang
Gao Huang
SSShiji Song
Shiji Song
XPXuran Pan
Xuran Pan
YXYitong Xia
Yitong Xia
CWCheng Wu
Cheng Wu
Data augmentation is widely known as a simple yet surprisingly effective technique for regularizing deep networks. Conventional data augmentation schemes, e.g., flipping, translation or rotation, are low-level, data-independent and class-agnostic operations, leading to limited diversity for augmented samples. To this end, we propose a novel semantic data augmentation algorithm to complement traditional approaches. The proposed method is inspired by the intriguing property that deep networks are effective in learning linearized features, i.e., certain directions in the deep feature space correspond to meaningful semantic transformations, e.g., changing the background or view angle of an object. Based on this observation, translating training samples along many such directions in the feature space can effectively augment the dataset for more diversity. To implement this idea, we first introduce a sampling based method to obtain semantically meaningful directions efficiently. Then, an upper bound of the expected cross-entropy (CE) loss on the augmented training set is derived by assuming the number of augmented samples goes to infinity, yielding a highly efficient algorithm. In fact, we show that the proposed implicit semantic data augmentation (ISDA) algorithm amounts to minimizing a novel robust CE loss, which adds minimal extra computational cost to a normal training procedure. In addition to supervised learning, ISDA can be applied to semi-supervised learning tasks under the consistency regularization framework, where ISDA amounts to minimizing the upper bound of the expected KL-divergence between the augmented features and the original features. Although being simple, ISDA consistently improves the generalization performance of popular deep models (e.g., ResNets and DenseNets) on a variety of datasets, i.e., CIFAR-10, CIFAR-100, SVHN, ImageNet, and Cityscapes. Code for reproducing our results is available at https://github.com/blackfeather-wang/ISDA-for-Deep-Networks .

18 January 2018 in IEEE Transactions on Systems, Man, and Cybernetics: Systems
Verified
Journal Article
Closed access
HWHui Wu
Hui Wu
SSShiji Song
Shiji Song
KYKeyou You
Keyou You
CWCheng Wu
Cheng Wu
In this paper, we consider depth control problems of an autonomous underwater vehicle (AUV) for tracking the desired depth trajectories. Due to the unknown dynamical model and the coupling between surge and yaw motions of the AUV, the problems cannot be effectively solved by most of the model-based or proportional-integral-derivative like controllers. To this purpose, we formulate the depth control problems of the AUV as continuous-state, continuous-action Markov decision processes under unknown transition probabilities. Based on the deterministic policy gradient theorem and neural network approximation, we propose a model-free reinforcement learning (RL) algorithm that learns a state-feedback controller from sampled trajectories of the AUV. To improve the performance of the RL algorithm, we further propose a batch-learning scheme through replaying previous prioritized trajectories. We illustrate with simulations that our model-free method is even comparable to the model-based controllers. Moreover, we validate the effectiveness of the proposed RL algorithm on a seafloor data set sampled from the South China Sea.

15 March 2018 in IEEE Transactions on Automatic Control
Verified
Journal Article
Closed access
PXPei Xie
Pei Xie
KYKeyou You
Keyou You
RTRoberto Tempo
Roberto Tempo
SSShiji Song
Shiji Song
CWCheng Wu
Cheng Wu
This paper considers a distributed convex optimization problem with inequality constraints over time-varying unbalanced digraphs, where the cost function is a sum of local objective functions, and each node of the graph only knows its local objective and inequality constraints. Although there is a vast body of literature on distributed optimization, most of them require the graph to be balanced, which is quite restrictive and not necessary. To solve it, this work proposes a novel idea of using the epigraph form of the constrained optimization, which can be easily used to study time-varying unbalanced digraphs. Under local communications, a simple iterative algorithm is then designed for each node. We prove that if the graph is uniformly jointly strongly connected, each node asymptotically converges to some common optimal solution.

10 April 2018 in IEEE Transactions on Cybernetics
Verified
Journal Article
Closed access
YCYiming Chen
Yiming Chen
SSShiji Song
Shiji Song
Shuang LiShuang Li
Shuang Li
LYLe Yang
Le Yang
CWCheng Wu
Cheng Wu
Extreme learning machine (ELM) has been applied in a wide range of classification and regression problems due to its high accuracy and efficiency. However, ELM can only deal with cases where training and testing data are from identical distribution, while in real world situations, this assumption is often violated. As a result, ELM performs poorly in domain adaptation problems, in which the training data (source domain) and testing data (target domain) are differently distributed but somehow related. In this paper, an ELM-based space learning algorithm, domain space transfer ELM (DST-ELM), is developed to deal with unsupervised domain adaptation problems. To be specific, through DST-ELM, the source and target data are reconstructed in a domain invariant space with target data labels unavailable. Two goals are achieved simultaneously. One is that, the target data are input into an ELM-based feature space learning network, and the output is supposed to approximate the input such that the target domain structural knowledge and the intrinsic discriminative information can be preserved as much as possible. The other one is that, the source data are projected into the same space as the target data and the distribution distance between the two domains is minimized in the space. This unsupervised feature transformation network is followed by an adaptive ELM classifier which is trained from the transferred labeled source samples, and is used for target data label prediction. Moreover, the ELMs in the proposed method, including both the space learning ELM and the classifier, require just a small number of hidden nodes, thus maintaining low computation complexity. Extensive experiments on real-world image and text datasets are conducted and verify that our approach outperforms several existing domain adaptation methods in terms of accuracy while maintaining high efficiency.

19 July 2019 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
YCYiming Chen
Yiming Chen
SSShiji Song
Shiji Song
Shuang LiShuang Li
Shuang Li
CWCheng Wu
Cheng Wu
Domain adaptation aims to deal with learning problems in which the labeled training data and unlabeled testing data are differently distributed. Maximum Mean Discrepancy (MMD), as a distribution distance measure, is minimized in various domain adaptation algorithms for eliminating domain divergence. We analyze empirical MMD from the point of view of graph embedding. It is discovered from the MMD intrinsic graph that, when the empirical MMD is minimized, the compactness within each domain and each class is simultaneously reduced. Therefore, points from different classes may mutually overlap, leading to unsatisfactory classification results. To deal with this issue, we present a graph embedding framework with intrinsic and penalty graphs for MMD-based domain adaptation algorithms. In the framework, we revise the intrinsic graph of MMD-based algorithms such that the within-class scatter is minimized, and thus the new features are discriminative. Two strategies are proposed. Based on the strategies, we instantiate the framework by exploiting four models. Each model has a penalty graph characterizing certain similarity property that should be avoided. Comprehensive experiments on visual cross-domain benchmark datasets demonstrate that the proposed models can greatly enhance the classification performance compared to state-of-the-art methods.

28 December 2018 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
WSWenjie Shi
Wenjie Shi
SSShiji Song
Shiji Song
CWCheng Wu
Cheng Wu
CCC.L. Philip Chen
C.L. Philip Chen
This paper investigates trajectory tracking problem for a class of underactuated autonomous underwater vehicles (AUVs) with unknown dynamics and constrained inputs. Different from existing policy gradient methods which employ single actor critic but cannot realize satisfactory tracking control accuracy and stable learning, our proposed algorithm can achieve high-level tracking control accuracy of AUVs and stable learning by applying a hybrid actors-critics architecture, where multiple actors and critics are trained to learn a deterministic policy and action-value function, respectively. Specifically, for the critics, the expected absolute Bellman error-based updating rule is used to choose the worst critic to be updated in each time step. Subsequently, to calculate the loss function with more accurate target value for the chosen critic, Pseudo Q-learning, which uses subgreedy policy to replace the greedy policy in Q-learning, is developed for continuous action spaces, and Multi Pseudo Q-learning (MPQ) is proposed to reduce the overestimation of action-value function and to stabilize the learning. As for the actors, deterministic policy gradient is applied to update the weights, and the final learned policy is defined as the average of all actors to avoid large but bad updates. Moreover, the stability analysis of the learning is given qualitatively. The effectiveness and generality of the proposed MPQ-based deterministic policy gradient (MPQ-DPG) algorithm are verified by the application on AUV with two different reference trajectories. In addition, the results demonstrate high-level tracking control accuracy and stable learning of MPQ-DPG. Besides, the results also validate that increasing the number of the actors and critics will further improve the performance.