no code implementations • 7 May 2024 • Yi Zuo, Lingling Li, Licheng Jiao, Fang Liu, Xu Liu, Wenping Ma, Shuyuan Yang, Yuwei Guo
In the first training stage, we focus on learning the spatial features (the features of object content) and breaking down the temporal relationships in the video frames by shuffling them.
no code implementations • 26 Apr 2024 • Yanbiao Ma, Licheng Jiao, Fang Liu, Lingling Li, Shuyuan Yang, Xu Liu
Our approach has the potential to change the paradigm of pseudo-label generation in semi-supervised learning.
1 code implementation • 22 Apr 2024 • Yanbiao Ma, Licheng Jiao, Fang Liu, Lingling Li, Wenping Ma, Shuyuan Yang, Xu Liu, Puhua Chen
Building fair deep neural networks (DNNs) is a crucial step towards achieving trustworthy artificial intelligence.
1 code implementation • 29 Mar 2024 • JianFeng Cai, Yue Ma, Zhixi Feng, Shuyuan Yang
Besides, this work has implications for how to efficiently utilize the multi-features of PolSAR data to learn better high-level representation in CL and how to construct networks suitable for PolSAR data better.
no code implementations • 21 Jan 2024 • Yanbiao Ma, Licheng Jiao, Fang Liu, Shuyuan Yang, Xu Liu, Puhua Chen
In this work, we propose to leverage the geometric information of the feature distribution of the well-represented head class to guide the model to learn the underlying distribution of the tail class.
no code implementations • 19 Jan 2024 • Wang Chao, Jiaxuan Zhao, Licheng Jiao, Lingling Li, Fang Liu, Shuyuan Yang
Pre-trained large language models (LLMs) have powerful capabilities for generating creative natural text.
no code implementations • 3 Nov 2023 • Yanbiao Ma, Licheng Jiao, Fang Liu, Shuyuan Yang, Xu Liu, Puhua Chen
In the context of the long-tail scenario, models exhibit a strong demand for high-quality data.
no code implementations • 16 Oct 2023 • Yanbiao Ma, Licheng Jiao, Fang Liu, Shuyuan Yang, Xu Liu, Lingling Li
The disadvantage is that these methods generally pursue models with balanced class accuracy on the data manifold, while ignoring the ability of the model to resist interference.
no code implementations • 24 Sep 2023 • Dan Wang, Licheng Jiao, Jie Chen, Shuyuan Yang, Fang Liu
After refinement, the changed pixels in the difference feature space are closer to each other, which facilitates change detection.
no code implementations • 2 Apr 2023 • Jiawei Zhang, Tiantian Wang, Zhixi Feng, Shuyuan Yang
Automatic modulation classification (AMC) is a crucial stage in the spectrum management, signal monitoring, and control of wireless communication systems.
2 code implementations • CVPR 2023 • Yanbiao Ma, Licheng Jiao, Fang Liu, Maoji Wen, Lingling Li, Wenping Ma, Shuyuan Yang, Xu Liu, Puhua Chen
To address the challenges of long-tailed classification, researchers have proposed several approaches to reduce model bias, most of which assume that classes with few samples are weak classes.
Ranked #19 on Long-tail Learning on CIFAR-10-LT (ρ=10)
no code implementations • 6 Feb 2023 • Chao Wang, Licheng Jiao, Jiaxuan Zhao, Lingling Li, Xu Liu, Fang Liu, Shuyuan Yang
It is computationally expensive to determine which LL Pareto weight in the LL Pareto weight set is the most appropriate for each UL solution.
no code implementations • 30 Dec 2022 • Yanbiao Ma, Licheng Jiao, Fang Liu, Yuxin Li, Shuyuan Yang, Xu Liu
Due to the prevalence of semantic scale imbalance, we propose semantic-scale-balanced learning, including a general loss improvement scheme and a dynamic re-weighting training framework that overcomes the challenge of calculating semantic scales in real-time during iterations.
no code implementations • 29 Jul 2022 • Yinghui Xing, Shuyuan Yang, Song Wang, Yan Zhang, Yanning Zhang
Most of the available deep learning-based pan-sharpening methods sharpen the multispectral images through a one-step scheme, which strongly depends on the reconstruction ability of the network.
no code implementations • 24 Mar 2022 • Yuting Yang, Licheng Jiao, Xu Liu, Fang Liu, Shuyuan Yang, Zhixi Feng, Xu Tang
Three image tasks and two video tasks of computer vision are investigated.
no code implementations • IEEE Transactions on Cybernetics 2021 • Xu Liu, Lingling Li, Fang Liu, Biao Hou, Shuyuan Yang, Licheng Jiao
Second, the group spatial attention and group spectral attention modules are proposed to extract image features.
no code implementations • IEEE Transactions on Neural Networks and Learning Systems 2021 • Licheng Jiao, Ruohan Zhang, Fang Liu, Shuyuan Yang, Biao Hou, Lingling Li, Xu Tang
Video object detection, a basic task in the computer vision field, is rapidly evolving and widely used.
1 code implementation • IEEE Transactions on Neural Networks and Learning Systems 2020 • Mengkun Liu, Licheng Jiao, Xu Liu, Lingling Li, Fang Liu, Shuyuan Yang
Second, the spatial-spectral feature fusion strategy is designed to incorporate the spectral features into CNN architecture.
no code implementations • 11 Jul 2019 • Licheng Jiao, Fan Zhang, Fang Liu, Shuyuan Yang, Lingling Li, Zhixi Feng, Rong Qu
Object detection is one of the most important and challenging branches of computer vision, which has been widely applied in peoples life, such as monitoring security, autonomous driving and so on, with the purpose of locating instances of semantic objects of a certain class.
no code implementations • 5 Sep 2018 • Yan Ju, Lingling Li, Licheng Jiao, Zhongle Ren, Biao Hou, Shuyuan Yang
Due to the limited amount and imbalanced classes of labeled training data, the conventional supervised learning can not ensure the discrimination of the learned feature for hyperspectral image (HSI) classification.
no code implementations • 1 Jul 2015 • Fang Liu, Junfei Shi, Licheng Jiao, Hongying Liu, Shuyuan Yang, Jie Wu, Hongxia Hao, Jialing Yuan
For polarimetric SAR (PolSAR) image classification, it is a challenge to classify the aggregated terrain types, such as the urban area, into semantic homogenous regions due to sharp bright-dark variations in intensity.