no code implementations • ECCV 2020 • Haifeng Xia, Zhengming Ding
Domain Adaptation as an important tool aims to explore a generalized model trained on well-annotated source knowledge to address learning issue on target domain with insufficient or even no annotation.
1 code implementation • 17 May 2023 • Anton Orlichenko, Gang Qu, Ziyu Zhou, Zhengming Ding, Yu-Ping Wang
We also find that both the decomposition and its residual have approximately equal predictive value, and when combined into an ensemble, exceed the AUC of FC-based prediction by up to 5%.
no code implementations • 12 Apr 2023 • Chen Zhao, Anqi Liu, Xiao Zhang, Xuewei Cao, Zhengming Ding, Qiuying Sha, Hui Shen, Hong-Wen Deng, Weihua Zhou
Integration of heterogeneous and high-dimensional multi-omics data is becoming increasingly important in understanding genetic data.
no code implementations • 5 Mar 2023 • Zheng Chen, Zhengming Ding, Jason M. Gregory, Lantao Liu
To improve the UDA-SS performance, we propose an Informed Domain Adaptation (IDA) model, a self-training framework that mixes the data based on class-level segmentation performance, which aims to emphasize small-region semantics during mixup.
1 code implementation • 4 Mar 2023 • Wenxiao Xiao, Zhengming Ding, Hongfu Liu
Many research efforts have been committed to unsupervised domain adaptation (DA) problems that transfer knowledge learned from a labeled source domain to an unlabeled target domain.
no code implementations • 20 Sep 2022 • Haifeng Xia, Pu, Wang, Toshiaki Koike-Akino, Ye Wang, Philip Orlik, Zhengming Ding
Domain adaptation (DA) aims to transfer the knowledge of a well-labeled source domain to facilitate unlabeled target learning.
no code implementations • 22 Aug 2022 • Qucheng Peng, Zhengming Ding, Lingjuan Lyu, Lichao Sun, Chen Chen
For the input-level, we design a new data augmentation technique as Phase MixUp, which highlights task-relevant objects in the interpolations, thus enhancing input-level regularization and class consistency for target models.
1 code implementation • 22 May 2022 • Wenxiao Xiao, Zhengming Ding, Hongfu Liu
In this paper, we revisit the concept of visual words and propose the Learnable Visual Words (LVW) to interpret the model prediction behaviors with two novel modules: semantic visual words learning and dual fidelity preservation.
no code implementations • 12 Apr 2022 • Wenju Zhang, Xiang Zhang, Qing Liao, Long Lan, Mengzhu Wang, Wei Wang, Baoyun Peng, Zhengming Ding
Nuclear norm maximization has shown the power to enhance the transferability of unsupervised domain adaptation model (UDA) in an empirical scheme.
2 code implementations • 5 Dec 2021 • Tina Chen, Taotao Jing, Renran Tian, Yaobin Chen, Joshua Domeyer, Heishiro Toyoda, Rini Sherony, Zhengming Ding
These innovative labels can enable several computer vision tasks, including pedestrian intent/behavior prediction, vehicle-pedestrian interaction segmentation, and video-to-language mapping for explainable algorithms.
1 code implementation • NeurIPS 2021 • Wenxiao Xiao, Zhengming Ding, Hongfu Liu
Partial Domain Adaptation (PDA) addresses the unsupervised domain adaptation problem where the target label space is a subset of the source label space.
1 code implementation • CVPR 2022 • Matias Mendieta, Taojiannan Yang, Pu Wang, Minwoo Lee, Zhengming Ding, Chen Chen
To alleviate this issue, many FL algorithms focus on mitigating the effects of data heterogeneity across clients by introducing a variety of proximal terms, some incurring considerable compute and/or memory overheads, to restrain local updates with respect to the global model.
no code implementations • 29 Oct 2021 • Zheng Chen, Zhengming Ding, David Crandall, Lantao Liu
Detecting navigable space is a fundamental capability for mobile robots navigating in unknown or unmapped environments.
no code implementations • 29 Sep 2021 • Haifeng Xia, Taotao Jing, Zizhan Zheng, Zhengming Ding
Unsupervised domain adaptation (UDA) aims to transfer knowledge from one or more well-labeled source domains to improve model performance on the different-yet-related target domain without any annotations.
1 code implementation • ICCV 2021 • Taotao Jing, Hongfu Liu, Zhengming Ding
In this paper, we propose a novel framework to accurately identify the seen categories in target domain, and effectively recover the semantic attributes for unseen categories.
3 code implementations • ICCV 2021 • Ce Zheng, Sijie Zhu, Matias Mendieta, Taojiannan Yang, Chen Chen, Zhengming Ding
Transformer architectures have become the model of choice in natural language processing and are now being introduced into computer vision tasks such as image classification, object detection, and semantic segmentation.
Ranked #9 on Monocular 3D Human Pose Estimation on Human3.6M
no code implementations • 25 Jan 2021 • Wei Wang, Baopu Li, Shuhui Yang, Jing Sun, Zhengming Ding, Junyang Chen, Xiao Dong, Zhihui Wang, Haojie Li
From the revealed unified JMMD, we illustrate that JMMD degrades the feature-label dependence (discriminability) that benefits to classification, and it is sensitive to the label distribution shift when the label kernel is the weighted class conditional one.
no code implementations • ICCV 2021 • Haifeng Xia, Handong Zhao, Zhengming Ding
Unsupervised Domain Adaptation solves knowledge transfer along with the coexistence of well-annotated source domain and unlabeled target instances.
no code implementations • 1 Jan 2021 • Haifeng Xia, Taotao Jing, Zhengming Ding
Batch Normalization (BN) as an important component assists Deep Neural Networks achieving promising performance for extensive learning tasks by scaling distribution of feature representations within mini-batches.
no code implementations • 28 Dec 2020 • Tao Zhang, Yang Cong, Gan Sun, Jiahua Dong, Yuyang Liu, Zhengming Ding
More specifically, we first do partial visual and tactile features extraction from the partial visual and tactile data, respectively, and encode the extracted features in modality-specific feature subspaces.
no code implementations • 8 Dec 2020 • Jiahua Dong, Yang Cong, Gan Sun, Yunsheng Yang, Xiaowei Xu, Zhengming Ding
Weakly-supervised learning has attracted growing research attention on medical lesions segmentation due to significant saving in pixel-level annotation cost.
no code implementations • 23 Oct 2020 • Taotao Jing, Bingrong Xu, Jingjing Li, Zhengming Ding
Such three strategies are formulated into a unified framework to address the fairness issue and domain shift challenge.
no code implementations • 27 Aug 2020 • Taotao Jing, Zhengming Ding
Unsupervised Domain adaptation (UDA) attempts to recognize the unlabeled target samples by building a learning model from a differently-distributed labeled source domain.
no code implementations • 27 Aug 2020 • Taotao Jing, Haifeng Xia, Zhengming Ding
Partial domain adaptation (PDA) attracts appealing attention as it deals with a realistic and challenging problem when the source domain label space substitutes the target domain.
no code implementations • 26 Aug 2020 • Taotao Jing, Ming Shao, Zhengming Ding
Partial domain adaptation aims to adapt knowledge from a larger and more diverse source domain to a smaller target domain with less number of classes, which has attracted appealing attention.
1 code implementation • 4 Aug 2020 • Shuang Li, Binhui Xie, Jiashu Wu, Ying Zhao, Chi Harold Liu, Zhengming Ding
In this paper, we propose a Simultaneous Semantic Alignment Network (SSAN) to simultaneously exploit correlations among categories and align the centroids for each category across domains.
no code implementations • 1 Jul 2020 • Wei Wang, Haojie Li, Zhengming Ding, Zhihui Wang
On the other hand, we design two different strategies to boost the feature discriminability: 1) we directly impose a trade-off parameter on the implicit intra-class distance in MMD to regulate its change; 2) we impose the similar weights revealed in MMD on inter-class distance and maximize it, then a balanced factor could be introduced to quantitatively leverage the relative importance between the feature transferability and its discriminability.
no code implementations • 16 Jun 2020 • Peizhao Li, Zhengming Ding, Hongfu Liu
Unsupervised domain adaptation targets to transfer task knowledge from labeled source domain to related yet unlabeled target domain, and is catching extensive interests from academic and industrial areas.
1 code implementation • 14 May 2020 • Shuang Li, Chi Harold Liu, Qiuxia Lin, Binhui Xie, Zhengming Ding, Gao Huang, Jian Tang
Most existing deep DA models only focus on aligning feature representations of task-specific layers across domains while integrating a totally shared convolutional architecture for source and target.
no code implementations • 8 May 2020 • Wei Wang, Zhihui Wang, Yuankai Xiang, Jing Sun, Haojie Li, Fuming Sun, Zhengming Ding
However, there are usually a large number of unlabeled data but only a few labeled data in the source domain, and how to transfer knowledge from this sparsely-labeled source domain to the target domain is still a challenge, which greatly limits their application in the wild.
1 code implementation • 10 Apr 2020 • Shuang Li, Chi Harold Liu, Qiuxia Lin, Qi Wen, Limin Su, Gao Huang, Zhengming Ding
Deep domain adaptation methods have achieved appealing performance by learning transferable representations from a well-labeled source domain to a different but related unlabeled target domain.
no code implementations • 29 Mar 2020 • Qianqian Wang, Zhengming Ding, Zhiqiang Tao, Quanxue Gao, Yun Fu
Nowadays, with the rapid development of data collection sources and feature extraction methods, multi-view data are getting easy to obtain and have received increasing research attention in recent years, among which, multi-view clustering (MVC) forms a mainstream research direction and is widely used in data analysis.
no code implementations • 4 Mar 2020 • Tongxin Wang, Zhengming Ding, Wei Shao, Haixu Tang, Kun Huang
Domain Adaptation (DA) targets at adapting a model trained over the well-labeled source domain to the unlabeled target domain lying in different distributions.
no code implementations • 12 Feb 2020 • Guanglei Yang, Haifeng Xia, Mingli Ding, Zhengming Ding
To balance the mitigation of domain gap and the preservation of the inherent structure, we propose a Bi-Directional Generation domain adaptation model with consistent classifiers interpolating two intermediate domains to bridge source and target domains.
no code implementations • 24 Dec 2019 • Wei Wang, Haojie Li, Zhihui Wang, Jing Sun, Zhengming Ding, Fuming Sun
Firstly, an importance filtered mechanism is devised to generate filtered soft labels to mitigate negative transfer desirably.
no code implementations • 28 Sep 2019 • Zhengming Ding, Yandong Guo, Lei Zhang, Yun Fu
Specifically, we target at building a more effective general face classifier for both normal persons and one-shot persons.
no code implementations • 28 Sep 2019 • Zhengming Ding, Ming Shao, Handong Zhao, Sheng Li
It is always demanding to learn robust visual representation for various learning problems; however, this learning and maintenance process usually suffers from noise, incompleteness or knowledge domain mismatch.
1 code implementation • 17 Sep 2019 • Jingjing Li, Erpeng Chen, Zhengming Ding, Lei Zhu, Ke Lu, Zi Huang
Domain adaptation investigates the problem of cross-domain knowledge transfer where the labeled source domain and unlabeled target domain have distinctive data distributions.
Ranked #2 on Domain Adaptation on USPS-to-MNIST
no code implementations • 9 Sep 2019 • Yucai Bai, Qin Zou, Xieyuanli Chen, Lingxi Li, Zhengming Ding, Long Chen
Given the fact that one same activity may be represented by videos in both high resolution (HR) and extreme low resolution (eLR), it is worth studying to utilize the relevant HR data to improve the eLR activity recognition.
no code implementations • CVPR 2019 • Zhengming Ding, Hongfu Liu
Zero-shot learning has been well explored to precisely identify new unobserved classes through a visual-semantic function obtained from the existing objects.
no code implementations • 31 May 2019 • Hongfu Liu, Zhiqiang Tao, Zhengming Ding
Consensus clustering fuses diverse basic partitions (i. e., clustering results obtained from conventional clustering methods) into an integrated one, which has attracted increasing attention in both academic and industrial areas due to its robust and effective performance.
1 code implementation • CVPR 2019 • Jingjing Li, Mengmeng Jin, Ke Lu, Zhengming Ding, Lei Zhu, Zi Huang
In this paper, we take the advantage of generative adversarial networks (GANs) and propose a novel method, named leveraging invariant side GAN (LisGAN), which can directly generate the unseen features from random noises which are conditioned by the semantic descriptions.
Ranked #4 on Generalized Zero-Shot Learning on SUN Attribute
no code implementations • ECCV 2018 • Zhengming Ding, Sheng Li, Ming Shao, Yun Fu
However, existing approaches separate target label optimization and domain-invariant feature learning as different steps.
1 code implementation • 18 Aug 2018 • Kai Li, Zhengming Ding, Kunpeng Li, Yulun Zhang, Yun Fu
To ensure scalability and separability, a softmax-like function is formulated to push apart the positive and negative support sets.
no code implementations • CVPR 2017 • Zhengming Ding, Ming Shao, Yun Fu
Zero-shot learning for visual recognition has received much interest in the most recent years.