no code implementations • 7 Jan 2025 • Zhenghao Feng, Lu Wen, Yuanyuan Xu, Binyu Yan, Xi Wu, Jiliu Zhou, Yan Wang
Additionally, based on a mean teacher framework, we elaborately design a balanced subclass regularization to utilize the teacher predictions of SCS task to supervise the student predictions of MoS task, thus effectively transferring unbiased knowledge to the MoS subnetwork and alleviating the influence of the class-imbalance problem.
no code implementations • 20 Dec 2024 • Ling Zhang, Zhichao Hou, Tingxiang Ji, Yuanyuan Xu, Runze Li
Model interpretability and explainability have garnered substantial attention in recent years, particularly in decision-making applications.
no code implementations • 30 Jul 2024 • Jiaqi Cui, Pinxian Zeng, Yuanyuan Xu, Xi Wu, Jiliu Zhou, Yan Wang
Our S3PET involves an un-supervised pre-training stage (Stage I) to extract representations from unpaired images, and a supervised dose-aware reconstruction stage (Stage II) to achieve LPET-to-SPET reconstruction by transferring the dose-specific knowledge between paired images.
1 code implementation • 8 Jul 2024 • Yuxiang Yang, Lu Wen, Xinyi Zeng, Yuanyuan Xu, Xi Wu, Jiliu Zhou, Yan Wang
Facial Expression Recognition (FER) holds significant importance in human-computer interactions.
Facial Expression Recognition
Facial Expression Recognition (FER)
+1
no code implementations • 23 Apr 2024 • Yuxiang Yang, Lu Wen, Yuanyuan Xu, Jiliu Zhou, Yan Wang
Universal Multi-source Domain Adaptation (UniMDA) transfers knowledge from multiple labeled source domains to an unlabeled target domain under domain shifts (different data distribution) and class shifts (unknown target classes).
no code implementations • 2 Apr 2024 • Yuchen Fei, Yanmei Luo, Yan Wang, Jiaqi Cui, Yuanyuan Xu, Jiliu Zhou, Dinggang Shen
In this paper, to reconstruct high-quality SPET images from multi-dose-level LPET images, we design a novel two-phase multi-dose-level PET reconstruction algorithm with dose level awareness, containing a pre-training phase and a SPET prediction phase.
no code implementations • 29 Feb 2024 • Jiaqi Cui, Yuanyuan Xu, Jianghong Xiao, Yuchen Fei, Jiliu Zhou, Xingcheng Peng, Yan Wang
Deep learning has facilitated the automation of radiotherapy by predicting accurate dose distribution maps.
1 code implementation • 21 Feb 2024 • Yiran Ding, Li Lyna Zhang, Chengruidong Zhang, Yuanyuan Xu, Ning Shang, Jiahang Xu, Fan Yang, Mao Yang
This is achieved by three key innovations: (i) we identify and exploit two forms of non-uniformities in positional interpolation through an efficient search, providing a better initialization for fine-tuning and enabling an 8x extension in non-fine-tuning scenarios; (ii) we introduce a progressive extension strategy that first fine-tunes a 256k length LLM and then conducts a second positional interpolation on the fine-tuned extended LLM to achieve a 2048k context window; (iii) we readjust LongRoPE on 8k length to recover the short context window performance.
no code implementations • 7 Feb 2024 • Lu Wen, Qihun Zhang, Zhenghao Feng, Yuanyuan Xu, Xiao Chen, Jiliu Zhou, Yan Wang
Radiotherapy is a primary treatment for cancers with the aim of applying sufficient radiation dose to the planning target volume (PTV) while minimizing dose hazards to the organs at risk (OARs).
no code implementations • 2 Feb 2024 • Haolei Pei, Yuanyuan Xu, Yangping Zhu, Yuan Nie
Industrial recommender systems usually consist of the retrieval stage and the ranking stage, to handle the billion-scale of users and items.
no code implementations • 6 Nov 2023 • Zhenghao Feng, Lu Wen, Jianghong Xiao, Yuanyuan Xu, Xi Wu, Jiliu Zhou, Xingchen Peng, Yan Wang
In the forward process, DiffDose transforms dose distribution maps into pure Gaussian noise by gradually adding small noise and a noise predictor is simultaneously trained to estimate the noise added at each timestep.
no code implementations • 17 Jun 2023 • Yuhan Wu, Yuanyuan Xu, Wenjie Zhang, Xiwei Xu, Ying Zhang
Research along this line suggests that using multi-modal distribution to represent answer entities is more suitable than uni-modal distribution, as a single query may contain multiple disjoint answer subsets due to the compositional nature of multi-hop queries and the varying latent semantics of relations.
1 code implementation • 2 May 2023 • Jingcai Guo, Song Guo, Shiheng Ma, Yuxia Sun, Yuanyuan Xu
Previous works usually assume the malware families are known to the classifier in a close-set scenario, i. e., testing families are the subset or at most identical to training families.
no code implementations • 2 May 2023 • Jingcai Guo, Yuanyuan Xu, Wenchao Xu, Yufeng Zhan, Yuxia Sun, Song Guo
Malware open-set recognition (MOSR) aims at jointly classifying malware samples from known families and detect the ones from novel unknown families, respectively.
no code implementations • 7 Mar 2022 • Ziming Liu, Song Guo, Jingcai Guo, Yuanyuan Xu, Fushuo Huo
We argue that disregarding the connection between major and minor classes, i. e., correspond to the global and local information, respectively, is the cause of the problem.
no code implementations • 20 Jan 2022 • Enyu Yu, DuanBing Chen, Yan Fu, Yuanyuan Xu
Because of its wide application, critical nodes identification has become an important research topic at the micro level of network science.
no code implementations • 8 Feb 2021 • Kevin Schnelli, Yuanyuan Xu
We show that the fluctuations of the largest eigenvalue of a real symmetric or complex Hermitian Wigner matrix of size $N$ converge to the Tracy--Widom laws at a rate $O(N^{-1/3+\omega})$, as $N$ tends to infinity.
Probability Mathematical Physics Mathematical Physics 15B52, 60B20
9 code implementations • 9 Nov 2019 • Yuanyuan Xu, Wan Yan, Haixin Sun, Genke Yang, Jiliang Luo
Face detection and alignment in unconstrained environment is always deployed on edge devices which have limited memory storage and low computing power.
Ranked #13 on
Face Detection
on WIDER Face (Hard)