Search Results for author: Zhengming Ding

Found 46 papers, 14 papers with code

HGNet: Hybrid Generative Network for Zero-shot Domain Adaptation

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.

Domain Adaptation

Angle Basis: a Generative Model and Decomposition for Functional Connectivity

1 code implementation17 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%.

IDA: Informed Domain Adaptive Semantic Segmentation

no code implementations5 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.

Data Augmentation Domain Adaptation +1

Visualizing Transferred Knowledge: An Interpretive Model of Unsupervised Domain Adaptation

1 code implementation4 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.

Unsupervised Domain Adaptation

Adversarial Bi-Regressor Network for Domain Adaptive Regression

no code implementations20 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.

Domain Adaptation regression

RAIN: RegulArization on Input and Network for Black-Box Domain Adaptation

no code implementations22 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.

Data Augmentation Self-Knowledge Distillation +1

Learnable Visual Words for Interpretable Image Recognition

1 code implementation22 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.

On the Equity of Nuclear Norm Maximization in Unsupervised Domain Adaptation

no code implementations12 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.

Image Classification Unsupervised Domain Adaptation

PSI: A Pedestrian Behavior Dataset for Socially Intelligent Autonomous Car

2 code implementations5 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.

Autonomous Vehicles

Implicit Semantic Response Alignment for Partial Domain Adaptation

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.

Partial Domain Adaptation Unsupervised Domain Adaptation

Local Learning Matters: Rethinking Data Heterogeneity in Federated Learning

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.

Federated Learning Privacy Preserving

Privacy Protected Multi-Domain Collaborative Learning

no code implementations29 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.

Unsupervised Domain Adaptation

Towards Novel Target Discovery Through Open-Set Domain Adaptation

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.

Domain Adaptation Open Set Learning

3D Human Pose Estimation with Spatial and Temporal Transformers

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.

Image Classification Monocular 3D Human Pose Estimation +3

A Unified Joint Maximum Mean Discrepancy for Domain Adaptation

no code implementations25 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.

Domain Adaptation

Adaptive Adversarial Network for Source-Free Domain Adaptation

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.

Source-Free Domain Adaptation Transfer Learning +1

Collaborative Normalization for Unsupervised Domain Adaptation

no code implementations1 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.

Unsupervised Domain Adaptation

Generative Partial Visual-Tactile Fused Object Clustering

no code implementations28 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.

Pseudo Label

Weakly-Supervised Cross-Domain Adaptation for Endoscopic Lesions Segmentation

no code implementations8 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.

Domain Adaptation Pseudo Label +1

Towards Fair Knowledge Transfer for Imbalanced Domain Adaptation

no code implementations23 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.

Domain Adaptation Fairness +1

Adversarial Dual Distinct Classifiers for Unsupervised Domain Adaptation

no code implementations27 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.

Unsupervised Domain Adaptation

Adaptively-Accumulated Knowledge Transfer for Partial Domain Adaptation

no code implementations27 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.

Partial Domain Adaptation Transfer Learning

Discriminative Cross-Domain Feature Learning for Partial Domain Adaptation

no code implementations26 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.

Partial Domain Adaptation

Simultaneous Semantic Alignment Network for Heterogeneous Domain Adaptation

1 code implementation4 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.

Domain Adaptation Pseudo Label

Rethink Maximum Mean Discrepancy for Domain Adaptation

no code implementations1 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.

Domain Adaptation

Mining Label Distribution Drift in Unsupervised Domain Adaptation

no code implementations16 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.

Unsupervised Domain Adaptation

Domain Conditioned Adaptation Network

1 code implementation14 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.

Domain Adaptation

Sparsely-Labeled Source Assisted Domain Adaptation

no code implementations8 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.

Domain Adaptation

Deep Residual Correction Network for Partial Domain Adaptation

1 code implementation10 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.

Partial Domain Adaptation

Generative Partial Multi-View Clustering

no code implementations29 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.


Towards Fair Cross-Domain Adaptation via Generative Learning

no code implementations4 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.

Domain Adaptation General Classification

Bi-Directional Generation for Unsupervised Domain Adaptation

no code implementations12 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.

Unsupervised Domain Adaptation

Importance Filtered Cross-Domain Adaptation

no code implementations24 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.

Domain Adaptation Object Recognition

Generative One-Shot Face Recognition

no code implementations28 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.

Face Recognition One-Shot Learning +1

Learning Robust Data Representation: A Knowledge Flow Perspective

no code implementations28 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.

Representation Learning Transfer Learning

Cycle-consistent Conditional Adversarial Transfer Networks

1 code implementation17 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.

Domain Adaptation Transfer Learning

Extreme Low Resolution Activity Recognition with Confident Spatial-Temporal Attention Transfer

no code implementations9 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.

Activity Recognition Privacy Preserving +1

Marginalized Latent Semantic Encoder for Zero-Shot Learning

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.

Graph Reconstruction Zero-Shot Learning

Consensus Clustering: An Embedding Perspective, Extension and Beyond

no code implementations31 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.

Domain Adaptation feature selection +2

Leveraging the Invariant Side of Generative Zero-Shot Learning

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.

Generalized Zero-Shot Learning

Support Neighbor Loss for Person Re-Identification

1 code implementation18 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.

Person Re-Identification

Cannot find the paper you are looking for? You can Submit a new open access paper.