no code implementations • 8 Oct 2023 • Yu-Huan Wu, Shi-Chen Zhang, Yun Liu, Le Zhang, Xin Zhan, Daquan Zhou, Jiashi Feng, Ming-Ming Cheng, Liangli Zhen
Semantic segmentation tasks naturally require high-resolution information for pixel-wise segmentation and global context information for class prediction.
1 code implementation • ICCV 2023 • Chi Zhang, Zhang Xiaoman, Ekanut Sotthiwat, Yanyu Xu, Ping Liu, Liangli Zhen, Yong liu
Federated learning has gained recognitions as a secure approach for safeguarding local private data in collaborative learning.
1 code implementation • ICLR 2022 • Jiawei Du, Hanshu Yan, Jiashi Feng, Joey Tianyi Zhou, Liangli Zhen, Rick Siow Mong Goh, Vincent Y. F. Tan
Recently, the relation between the sharpness of the loss landscape and the generalization error has been established by Foret et al. (2020), in which the Sharpness Aware Minimizer (SAM) was proposed to mitigate the degradation of the generalization.
no code implementations • 20 Jun 2021 • Ping Liu, Yuewei Lin, Yang He, Yunchao Wei, Liangli Zhen, Joey Tianyi Zhou, Rick Siow Mong Goh, Jingen Liu
In this paper, we propose to utilize Automated Machine Learning to adaptively search a neural architecture for deepfake detection.
1 code implementation • CVPR 2021 • Peng Hu, Xi Peng, Hongyuan Zhu, Liangli Zhen, Jie Lin
Recently, cross-modal retrieval is emerging with the help of deep multimodal learning.
no code implementations • Findings (ACL) 2021 • Hao Zhang, Aixin Sun, Wei Jing, Liangli Zhen, Joey Tianyi Zhou, Rick Siow Mong Goh
In this work, we propose a Parallel Attention Network with Sequence matching (SeqPAN) to address the challenges in this task: multi-modal representation learning, and target moment boundary prediction.
1 code implementation • 13 May 2021 • Hao Zhang, Aixin Sun, Wei Jing, Guoshun Nan, Liangli Zhen, Joey Tianyi Zhou, Rick Siow Mong Goh
We adopt the first approach and introduce two contrastive learning objectives to refine video encoder and text encoder to learn video and text representations separately but with better alignment for VCMR.
no code implementations • 26 Feb 2021 • Hao Zhang, Aixin Sun, Wei Jing, Liangli Zhen, Joey Tianyi Zhou, Rick Siow Mong Goh
Our study suggests that the span-based QA framework is an effective strategy to solve the NLVL problem.
1 code implementation • CVPR 2019 • Liangli Zhen, Peng Hu, Xu Wang, Dezhong Peng
Furthermore, it simultaneously minimises the modality invariance loss and uses a weight sharing strategy to eliminate the cross-modal discrepancy of multimedia data in the common representation space to learn modality-invariant features.
no code implementations • 7 Jun 2018 • Liangli Zhen, Miqing Li, Ran Cheng, Dezhong Peng, Xin Yao
The redundancy of some objectives can lead to the multiobjective problem having a degenerate Pareto front, i. e., the dimension of the Pareto front of the $m$-objective problem be less than (m-1).
no code implementations • 15 May 2017 • Liangli Zhen, Dezhong Peng, Wei Wang, Xin Yao
Our method has the advantages of a closed-form solution and the capacity of clustering data points that lie on nonlinear subspaces.
no code implementations • 30 Apr 2017 • Miqing Li, Liangli Zhen, Xin Yao
In this paper, we make some observations of the parallel coordinates plot, in terms of comparing the quality of solution sets, understanding the shape and distribution of a solution set, and reflecting the relation between objectives.
no code implementations • 24 Apr 2013 • Liangli Zhen, Zhang Yi, Xi Peng, Dezhong Peng
There are two popular schemes to construct a similarity graph, i. e., pairwise distance based scheme and linear representation based scheme.