Lichen Wang

Lichen Wang

Auto-generated profile, based on publicly available information

Lichen Wang

Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

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

Representative Publications

View All Publications
6 October 2018
Verified
Book Chapter
Closed access
PDF file
YZYulun Zhang
Yulun Zhang
KLKunpeng Li
Kunpeng Li
KLKai Li
Kai Li
LWLichen Wang
Lichen Wang
Bineng ZhongBineng Zhong
Bineng Zhong
YFYun Fu
Yun Fu

9 November 2022 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
CQCan Qin
Can Qin
LWLichen Wang
Lichen Wang
QMQianqian Ma
Qianqian Ma
YYYu Yin
Yu Yin
HWHuan Wang
Huan Wang
YFYun Fu
Yun Fu
Semi-supervised domain adaptation (SSDA) is quite a challenging problem requiring methods to overcome both 1) overfitting towards poorly annotated data and 2) distribution shift across domains. Unfortunately, a simple combination of domain adaptation (DA) and semi-supervised learning (SSL) methods often fail to address such two objects because of training data bias towards labeled samples. In this paper, we introduce an adaptive structure learning method to regularize the cooperation of SSL and DA. Inspired by the multi-views learning, our proposed framework is composed of a shared feature encoder network and two classifier networks, trained for contradictory purposes. Among them, one of the classifiers is applied to group target features to improve intra-class density, enlarging the gap of categorical clusters for robust representation learning. Meanwhile, the other classifier, serviced as a regularizer, attempts to scatter the source features to enhance the smoothness of the decision boundary. The iterations of target clustering and source expansion make the target features being well-enclosed inside the dilated boundary of the corresponding source points. For the joint address of cross-domain features alignment and partially labeled data learning, we apply the maximum mean discrepancy (MMD) distance minimization and self-training (ST) to project the contradictory structures into a shared view to make the reliable final decision. The experimental results over the standard SSDA benchmarks, including DomainNet and Office-home, demonstrate both the accuracy and robustness of our method over the state-of-the-art approaches.

18 September 2018 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
LWLichen Wang
Lichen Wang
Zhengming DingZhengming Ding
Zhengming Ding
YFYun Fu
Yun Fu
Human motion segmentation has a great potential in real-world applications. Conventional segmentation approaches cluster data with no guidance from prior knowledge, which could easily cause unpredictable segmentation output and decrease the performance. To this end, we seek to improve the human-motion segmentation performance by fully utilizing pre-existing well-labeled source data. Specifically, we design a new transfer subspace clustering method for motion segmentation with a weighted rank constraint. Specifically, our proposed model obtains the representations of both source and target sequences by mitigating their distribution divergence, which allows for more effective knowledge transfer to the target. To guide new representation learning, we designed a novel sequential graph to preserve temporal information residing in both the source and the target. Furthermore, a weighted low-rank constraint is added to enforce the graph regularizer and uncover clustering structures within data. Experiments are evaluated on four human motion databases, which prove the enhanced performance and increased stability of our model compared with state-of-the-art baselines.

3 November 2021 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
LWLichen Wang
Lichen Wang
YLYunyu Liu
Yunyu Liu
HDHang Di
Hang Di
CQCan Qin
Can Qin
Gan SunGan Sun
Gan Sun
YFYun Fu
Yun Fu
In a real-world scenario, an object could contain multiple tags instead of a single categorical label. To this end, multi-label learning (MLL) emerged. In MLL, the feature distributions are long-tailed and the complex semantic label relation and the long-tailed training samples are the main challenges. Semi-supervised learning is a potential solution. While, existing methods are mainly designed for single class scenario while ignoring the latent label relations. In addition, they cannot well handle the distribution shift commonly existing across source and target domains. To this end, a Semi-supervised Dual Relation Learning (SDRL) framework for multi-label classification is proposed. SDRL utilizes a few labeled samples as well as large scale unlabeled samples in the training stage. It jointly explores the inter-instance feature-level relation and the intra-instance label-level relation even from the unlabeled samples. In our model, a dual-classifier structure is deployed to obtain domain invariant representations. The prediction results from the classifiers are further compared and the most confident predictions are extracted as pseudo labels. A trainable label relation tensor is designed to explicitly explore the pairwise latent label relations and refine the predicted labels. SDRL is able to effectively and efficiently explore the feature-label relation as well as the label-label relation knowledge without any extra semantic knowledge. We evaluated SDRL in general and zero-shot multi-label classification tasks and we concluded that SDRL is superior to other SOTA baselines. Furthermore, extensive ablation studies have been done which reveal the effectiveness of each component in our framework.

13 November 2020
Verified
Book Chapter
Closed access
PDF file
YLYunyu Liu
Yunyu Liu
LWLichen Wang
Lichen Wang
YBYue Bai
Yue Bai
CQCan Qin
Can Qin
Zhengming DingZhengming Ding
Zhengming Ding
YFYun Fu
Yun Fu

22 December 2022 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
YBYue Bai
Yue Bai
LWLichen Wang
Lichen Wang
YLYunyu Liu
Yunyu Liu
YYYu Yin
Yu Yin
HDHang Di
Hang Di
YFYun Fu
Yun Fu
Human motion segmentation (HMS) aims to segment a long human action video into a bunch of short and meaningful action clips. Existing supervised learning approaches need a large amount of training data which may be costly in real-world scenario, while most unsupervised clustering methods cannot fully explore the temporal correlations among human motions and hard to achieve promising performances. In our paper, we design a novel unsupervised framework, called Velocity-Sensitive Dual-Side Auto-Encoder (VSDA), for HMS task. Specifically, a multi-neighbor auto-encoder (MNA) is proposed to extract informative temporal features, which fully explores the local temporal patterns of human motions. In addition, a long-short distance encoding (LSE) strategy is designed. It constrains the encoded representations of close (short-distance) frames becoming similar while the representations of far-away (long-distance) frames becoming distinctive. Similarly, this strategy is also deployed on the decoded outputs as the long-short distance decoding (LSD) module. The LSE/LSD guides the learning process explicitly and implicitly to achieve the dual-side structure. Moreover, we consider the energy variations during the human motion to propose the velocity-sensitive (VS) guidance mechanism for further model improvement. VSDA leverages the temporal characteristics of human motion and derives promising HMS performance. Comprehensive experiments on six real-world human motion datasets illustrate the effectiveness of our proposed model.