no code implementations • ECCV 2020 • Xiaobo Wang, Tianyu Fu, Shengcai Liao, Shuo Wang, Zhen Lei, Tao Mei
Knowledge distillation is an effective tool to compress large pre-trained Convolutional Neural Networks (CNNs) or their ensembles into models applicable to mobile and embedded devices.
no code implementations • 5 Feb 2025 • Dawei Lu, Deqiang Xiao, Danni Ai, Jingfan Fan, Tianyu Fu, Yucong Lin, Hong Song, Xujiong Ye, Lei Zhang, Jian Yang
Given that RGB and depth images are two views of the same endoscopic surgery scene, in this paper, we introduce a novel concept referred as ``meta feature embedding (MetaFE)", in which the physical entities (e. g., tissues and surgical instruments) of endoscopic surgery are represented using the shared features that can be alternatively decoded into RGB or depth image.
1 code implementation • 30 Dec 2024 • Tianyu Fu, Tengxuan Liu, Qinghao Han, Guohao Dai, Shengen Yan, Huazhong Yang, Xuefei Ning, Yu Wang
Leveraging the unique properties of similarity over importance, we introduce FrameFusion, a novel approach that combines similarity-based merging with importance-based pruning for better token reduction in LVLMs.
no code implementations • 3 Nov 2024 • Liang Bai, Hong Song, Yucong Lin, Tianyu Fu, Deqiang Xiao, Danni Ai, Jingfan Fan, Jian Yang
Additionally, we introduce a similarity-based feature compensation mechanism that integrates generated old class features with similar new class features to synthesize robust retrospective representations.
no code implementations • 19 Jul 2024 • Mingyang Lei, Jingfan Fan, Long Shao, Hong Song, Deqiang Xiao, Danni Ai, Tianyu Fu, Ying Gu, Jian Yang
Within PDCNet, a Transformer branch is used to capture global perception in the fringe images, while a CNN branch is designed to collect local details in the speckle images.
1 code implementation • 11 Jul 2024 • Minghui Wu, Chenxu Zhao, Anyang Su, Donglin Di, Tianyu Fu, Da An, Min He, Ya Gao, Meng Ma, Kun Yan, Ping Wang
Along with the dataset, we designed a Hypergraph Multi-modal Large Language Model (HMLLM) to explore the associations among different demographics, video elements, EEG, and eye-tracking indicators.
1 code implementation • 21 Jun 2024 • Tianyu Fu, Haofeng Huang, Xuefei Ning, Genghan Zhang, Boju Chen, Tianqi Wu, Hongyi Wang, Zixiao Huang, Shiyao Li, Shengen Yan, Guohao Dai, Huazhong Yang, Yu Wang
Existing methods typically employ a uniform sparse attention mask, applying the same sparse pattern across different attention heads and input lengths.
1 code implementation • 20 Jun 2024 • Xuefei Ning, Zifu Wang, Shiyao Li, Zinan Lin, Peiran Yao, Tianyu Fu, Matthew B. Blaschko, Guohao Dai, Huazhong Yang, Yu Wang
We reveal some findings: (1) Teaching materials that make it easier for students to learn have clearer and more accurate logic when using in-context learning as the student's "learning" method; (2) Weak-to-strong generalization: LbT might help improve strong models by teaching weak models; (3) Diversity in students might help: teaching multiple students could be better than teaching one student or the teacher itself.
no code implementations • 22 Apr 2024 • Zixuan Zhou, Xuefei Ning, Ke Hong, Tianyu Fu, Jiaming Xu, Shiyao Li, Yuming Lou, Luning Wang, Zhihang Yuan, Xiuhong Li, Shengen Yan, Guohao Dai, Xiao-Ping Zhang, Yuhan Dong, Yu Wang
This paper presents a comprehensive survey of the existing literature on efficient LLM inference.
no code implementations • 22 Feb 2024 • Rex Ying, Tianyu Fu, Andrew Wang, Jiaxuan You, Yu Wang, Jure Leskovec
SPMiner combines graph neural networks, order embedding space, and an efficient search strategy to identify network subgraph patterns that appear most frequently in the target graph.
no code implementations • 8 Jan 2024 • Shulin Zeng, Jun Liu, Guohao Dai, Xinhao Yang, Tianyu Fu, Hongyi Wang, Wenheng Ma, Hanbo Sun, Shiyao Li, Zixiao Huang, Yadong Dai, Jintao Li, Zehao Wang, Ruoyu Zhang, Kairui Wen, Xuefei Ning, Yu Wang
However, existing GPU and transformer-based accelerators cannot efficiently process compressed LLMs, due to the following unresolved challenges: low computational efficiency, underutilized memory bandwidth, and large compilation overheads.
1 code implementation • 16 Aug 2023 • Tianyu Fu, Chiyue Wei, Yu Wang, Rex Ying
We introduce DeSCo, a scalable neural deep subgraph counting pipeline, designed to accurately predict both the count and occurrence position of queries on target graphs post single training.
no code implementations • 4 Nov 2022 • Yucong Lin, Jinhua Su, Yuhang Li, Yuhao Wei, Hanchao Yan, Saining Zhang, Jiaan Luo, Danni Ai, Hong Song, Jingfan Fan, Tianyu Fu, Deqiang Xiao, Feifei Wang, Jue Hou, Jian Yang
Deep learning methods have contributed substantially to the rapid advancement of medical image segmentation, the quality of which relies on the suitable design of loss functions.
no code implementations • 26 Nov 2019 • Xiaobo Wang, Shifeng Zhang, Shuo Wang, Tianyu Fu, Hailin Shi, Tao Mei
Face recognition has witnessed significant progress due to the advances of deep convolutional neural networks (CNNs), the central task of which is how to improve the feature discrimination.
no code implementations • 29 Apr 2019 • Yunxiao Qin, Chenxu Zhao, Xiangyu Zhu, Zezheng Wang, Zitong Yu, Tianyu Fu, Feng Zhou, Jingping Shi, Zhen Lei
Therefore, we define face anti-spoofing as a zero- and few-shot learning problem.
no code implementations • 20 Jan 2019 • Shifeng Zhang, Rui Zhu, Xiaobo Wang, Hailin Shi, Tianyu Fu, Shuo Wang, Tao Mei, Stan Z. Li
With the availability of face detection benchmark WIDER FACE dataset, much of the progresses have been made by various algorithms in recent years.
4 code implementations • 29 Dec 2018 • Xiaobo Wang, Shuo Wang, Shifeng Zhang, Tianyu Fu, Hailin Shi, Tao Mei
Face recognition has witnessed significant progresses due to the advances of deep convolutional neural networks (CNNs), the central challenge of which, is feature discrimination.
Ranked #1 on
Face Identification
on Trillion Pairs Dataset