Search

Your search keyword '"LIU Ping"' showing total 585 results
Start Over Author "LIU Ping" Publisher ieee
585 results on '"LIU Ping"'

33. Adversarial Semantic Hallucination for Domain Generalized Semantic Segmentation

Author

Tjio, Gabriel, Liu, Ping, Zhou, Joey Tianyi, and Goh, Rick Siow Mong

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

Convolutional neural networks typically perform poorly when the test (target domain) and training (source domain) data have significantly different distributions. While this problem can be mitigated by using the target domain data to align the source and target domain feature representations, the target domain data may be unavailable due to privacy concerns. Consequently, there is a need for methods that generalize well despite restricted access to target domain data during training. In this work, we propose an adversarial semantic hallucination approach (ASH), which combines a class-conditioned hallucination module and a semantic segmentation module. Since the segmentation performance varies across different classes, we design a semantic-conditioned style hallucination module to generate affine transformation parameters from semantic information in the segmentation probability maps of the source domain image. Unlike previous adaptation approaches, which treat all classes equally, ASH considers the class-wise differences. The segmentation module and the hallucination module compete adversarially, with the hallucination module generating increasingly "difficult" stylized images to challenge the segmentation module. In response, the segmentation module improves as it is trained with generated samples at an appropriate class-wise difficulty level. Our results on the Cityscapes and Mapillary benchmark datasets show that our method is competitive with state of the art work. Code is made available at https://github.com/gabriel-tjio/ASH., Comment: Accepted in WACV 2022

Published
2022

44. New Discontinuous Space Vector Modulation Strategies for Impedance-Source Inverter With Superior Thermal and Harmonic Performance.

Author

Liu, Ping, Xu, Jie, Sun, Meidi, Yuan, Jing, and Blaabjerg, Frede

Subjects
*VECTOR spaces, *THERMAL stresses, *ELECTROSTATIC induction
Abstract

Impedance-source inverters provide a promising single-stage power conversion with boost-buck capabilities and inverter legs short-circuit immunity. To achieve superior thermal and output harmonic performance, two novel discontinuous modulation strategies for the three-phase quasi-Z source inverter, called the maximum-boost discontinuous space vector modulation (SVM) and the simple-boost discontinuous SVM respectively, are proposed in this article. By properly arranging the shoot-through states and clamping a certain switch to the positive or negative dc-link rail during one-third of the fundamental period, reduced thermal stresses and superior total harmonic distortion performance can be achieved. The proposed modulation strategies are analyzed and compared to the conventional ones in terms of current stresses, power losses, thermal stresses, and output harmonics. Finally, simulations and experimental tests are carried out to validate the performance of the proposed modulation strategies and verify the presented analysis. [ABSTRACT FROM AUTHOR]

Published
2022
Full Text
View/download PDF

45. Point Adversarial Self-Mining: A Simple Method for Facial Expression Recognition.

Author

Liu, Ping, Lin, Yuewei, Meng, Zibo, Lu, Lu, Deng, Weihong, Zhou, Joey Tianyi, and Yang, Yi

Abstract

In this article, we propose a simple yet effective approach, called point adversarial self mining (PASM), to improve the recognition accuracy in facial expression recognition (FER). Unlike previous works focusing on designing specific architectures or loss functions to solve this problem, PASM boosts the network capability by simulating human learning processes: providing updated learning materials and guidance from more capable teachers. Specifically, to generate new learning materials, PASM leverages a point adversarial attack method and a trained teacher network to locate the most informative position related to the target task, generating harder learning samples to refine the network. The searched position is highly adaptive since it considers both the statistical information of each sample and the teacher network capability. Other than being provided new learning materials, the student network also receives guidance from the teacher network. After the student network finishes training, the student network changes its role and acts as a teacher, generating new learning materials and providing stronger guidance to train a better student network. The adaptive learning materials generation and teacher/student update can be conducted more than one time, improving the network capability iteratively. Extensive experimental results validate the efficacy of our method over the existing state of the arts for FER. [ABSTRACT FROM AUTHOR]

Published
2022
Full Text
View/download PDF

46. Knowledge Graph Embedding by Double Limit Scoring Loss.

Author

Zhou, Xiaofei, Niu, Lingfeng, Zhu, Qiannan, Zhu, Xingquan, Liu, Ping, Tan, Jianlong, and Guo, Li

Subjects
KNOWLEDGE graphs, SPARSE matrices
Abstract

Knowledge graph embedding is an effective way to represent knowledge graph, which greatly enhance the performances on knowledge graph completion tasks, e.g., entity or relation prediction. For knowledge graph embedding models, designing a powerful loss framework is crucial to the discrimination between correct and incorrect triplets. Margin-based ranking loss is a commonly used negative sampling framework to make a suitable margin between the scores of positive and negative triples. However, this loss can not ensure ideal low scores for the positive triplets and high scores for the negative triplets, which is not beneficial for knowledge completion tasks. In this paper, we present a double limit scoring loss to separately set upper bound for correct triplets and lower bound for incorrect triplets, which provides more effective and flexible optimization for knowledge graph embedding. Upon the presented loss framework, we present several knowledge graph embedding models including TransE-SS, TransH-SS, TransD-SS, ProjE-SS and ComplEx-SS. The experimental results on link prediction and triplet classification show that our proposed models have the significant improvement compared to state-of-the-art baselines. [ABSTRACT FROM AUTHOR]

Published
2022
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results