Search

Your search keyword '"Ding, Zhengming"' showing total 381 results
Start Over Author "Ding, Zhengming"

Refine your results

more »

more »

more »

more »
381 results on '"Ding, Zhengming"'

117. Generative Partial Visual-Tactile Fused Object Clustering

Author

Zhang, Tao, Cong, Yang, Sun, Gan, Dong, Jiahua, Liu, Yuyang, and Ding, Zhengming

Subjects
FOS: Computer and information sciences, Computer Science - Robotics, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, General Medicine, Robotics (cs.RO)
Abstract

Visual-tactile fused sensing for object clustering has achieved significant progresses recently, since the involvement of tactile modality can effectively improve clustering performance. However, the missing data (i.e., partial data) issues always happen due to occlusion and noises during the data collecting process. This issue is not well solved by most existing partial multi-view clustering methods for the heterogeneous modality challenge. Naively employing these methods would inevitably induce a negative effect and further hurt the performance. To solve the mentioned challenges, we propose a Generative Partial Visual-Tactile Fused (i.e., GPVTF) framework for object clustering. 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. A conditional cross-modal clustering generative adversarial network is then developed to synthesize one modality conditioning on the other modality, which can compensate missing samples and align the visual and tactile modalities naturally by adversarial learning. To the end, two pseudo-label based KL-divergence losses are employed to update the corresponding modality-specific encoders. Extensive comparative experiments on three public visual-tactile datasets prove the effectiveness of our method., 9 pages; 8 figures

Published
2021

130. Towards Fair Knowledge Transfer for Imbalanced Domain Adaptation

Author

Jing, Taotao, Xu, Bingrong, Li, Jingjing, and Ding, Zhengming

Subjects
Structure (mathematical logic), FOS: Computer and information sciences, Computer science, business.industry, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, Boundary (topology), Machine learning, computer.software_genre, Computer Graphics and Computer-Aided Design, Domain (software engineering), Data modeling, Classifier (linguistics), Artificial intelligence, Set (psychology), business, Adaptation (computer science), Knowledge transfer, computer, Software
Abstract

Domain adaptation (DA) becomes an up-and-coming technique to address the insufficient or no annotation issue by exploiting external source knowledge. Existing DA algorithms mainly focus on practical knowledge transfer through domain alignment. Unfortunately, they ignore the fairness issue when the auxiliary source is extremely imbalanced across different categories, which results in severe under-presented knowledge adaptation of minority source set. To this end, we propose a Towards Fair Knowledge Transfer (TFKT) framework to handle the fairness challenge in imbalanced cross-domain learning. Specifically, a novel cross-domain knowledge propagation technique is proposed with the guidance of within-source and cross-domain structure graphs to smooth the manifold of the minority source set. Besides, a cross-domain fulfillment augmentation strategy is exploited achieve domain adaptation. Moreover, hybrid distinct classifiers and cross-domain prototype alignment are adopted to seek a more robust classifier boundary and mitigate the domain shift. Such three strategies are formulated into a unified framework to address the fairness issue and domain shift challenge. Extensive experiments over two popular benchmarks have verified the effectiveness of our proposed model by comparing to existing state-of-the-art DA models, and especially our model significantly improves over 20% on two benchmarks in terms of the overall accuracy.

Published
2021

140. Lifelong Visual-Tactile Spectral Clustering for Robotic Object Perception

Author

Liu, Yuyang, Cong, Yang, Sun, Gan, and Ding, Zhengming

Abstract

This work presents a novel visual-tactile fused clustering framework, called Lifelong Visual-Tactile Spectral Clustering (i.e., LVTSC), to effectively learn consecutive object clustering tasks for robotic perception. Lifelong learning has become an important and hot topic in recent studies on machine learning, aiming to imitate “human learning” and reduce the computational cost when consecutively learning new tasks. Our proposed LVTSC model explores the knowledge transfer and representation correlation from a local modality-invariant perspective under modality-consistent constraint guidance. For the modality-invariant part, we design a set of modality-invariant basis libraries to capture the latent clustering centers of each modality and a set of modality-invariant feature libraries to forcibly embed the manifold information of each modality. A modal-consistent constraint reinforces the correlation between visual and tactile modalities by maximizing the feature manifold correspondences. When the object clustering task comes continuously, the overall objective is optimized by an effective alternating direction method with guaranteed convergence. Our proposed LVTSC framework has been extensively validated for its effectiveness and efficiency on the three challenging real-world robotic object perception datasets.

Published
2023
Full Text
View/download PDF

141. Maximum Structural Generation Discrepancy for Unsupervised Domain Adaptation

Author

Xia, Haifeng, Jing, Taotao, and Ding, Zhengming

Abstract

Unsupervised domain adaptation (UDA) has recently become an appealing research topic in visual recognition, since it exploits all accessible well-labeled source data to train a model with high generalization on target domain without any annotations. However, due to the significant domain discrepancy, the bottleneck for UDA is to learn effective domain-invariant feature representations. To fight off such an obstacle, we propose a novel cross-domain learning framework named Maximum Structural Generation Discrepancy (MSGD) to accurately estimate and mitigate domain shift via introducing an intermediate domain. First, the cross-domain topological structure is explored to propagate target samples to generate a novel intermediate domain paired with the specific source instances. The intermediate domain plays as the bridge to gradually reduce distribution divergence across source and target domains. Concretely, the similar category semantic across source and intermediate features tends to naturally conduct the class-level alignment on eliminating their domain shift. In terms of no target annotation, the domain-level alignment manner is suitable to narrow down the distance between intermediate and target domains. Moreover, to produce high-quality generative instances, we develop the class-driven collaborative translation (CDCT) module to generate class-consistent cross-domain samples in each mini-batch with the assistance of pseudo-labels. Extensive experimental analyses on five domain adaptation benchmarks demonstrate the effectiveness of our MSGD on solving UDA problem.

Published
2023
Full Text
View/download PDF

142. What and How: Generalized Lifelong Spectral Clustering via Dual Memory.

Author

Sun, Gan, Cong, Yang, Dong, Jiahua, Liu, Yuyang, Ding, Zhengming, and Yu, Haibin

Subjects
HIERARCHICAL clustering (Cluster analysis), MEMORY, KNOWLEDGE transfer, TASK performance, INTUITION
Abstract

Spectral clustering (SC) has become one of the most widely-adopted clustering algorithms, and been successfully applied into various applications. We in this work explore the problem of spectral clustering in a lifelong learning framework termed as Generalized Lifelong Spectral Clustering (GL $^2$ 2 SC). Different from most current studies, which concentrate on a fixed spectral clustering task set and cannot efficiently incorporate a new clustering task, the goal of our work is to establish a generalized model for new spectral clustering tasks by “What” and “How” to lifelong learn from past tasks. In respect of “what to lifelong learn”, our GL $^2$ 2 SC framework contains a dual memory mechanism with a deep orthogonal factorization manner: an orthogonal basis memory stores hidden and hierarchical clustering centers among learned tasks, and a feature embedding memory captures deep manifold representation common across multiple related tasks. When learning a new clustering task, the intuition here for “how to lifelong learn” is that GL $^2$ 2 SC can transfer intrinsic knowledge from dual memory mechanism to obtain task-specific encoding matrix. Then the encoding matrix can redefine the dual memory over time to provide maximal benefits when learning future tasks, and reversely maximize performance for past tasks. To achieve this, we propose an alternative optimization formulation with convergence guarantee for solving our GL $^2$ 2 SC model. To the end, empirical comparisons on several benchmark datasets show the effectiveness of our GL $^2$ 2 SC, in comparison with several state-of-the-art clustering models. [ABSTRACT FROM AUTHOR]

Published
2022
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results