1 code implementation • 19 Nov 2024 • Chuan He, Yongchao Liu, Qiang Li, Weiqiang Wang, Xin Fu, Xinyi Fu, Chuntao Hong, Xinwei Yao
Secondly, a novel multi-scale transformer architecture equipped with multi-grained user preference extraction is proposed to encode the interaction-aware sequential pattern enhanced by capturing temporal behavior-aware multi-grained preference .
no code implementations • 1 May 2024 • Huai-an Su, Jiaxiang Geng, Liang Li, Xiaoqi Qin, Yanzhao Hou, Hao Wang, Xin Fu, Miao Pan
Although such fixed size subnetwork assignment enables FL training over heterogeneous mobile devices, it is unaware of (i) the dynamic changes of devices' communication and computing conditions and (ii) FL training progress and its dynamic requirements of local training contributions, both of which may cause very long FL training delay.
no code implementations • 6 Mar 2023 • Jiafu Wu, Mufeng Yao, Dong Wu, Mingmin Chi, Baokun Wang, Ruofan Wu, Xin Fu, Changhua Meng, Weiqiang Wang
Graph representation plays an important role in the field of financial risk control, where the relationship among users can be constructed in a graph manner.
no code implementations • ICCV 2023 • Rui Chen, Qiyu Wan, Pavana Prakash, Lan Zhang, Xu Yuan, Yanmin Gong, Xin Fu, Miao Pan
However, practical deployment of FL over mobile devices is very challenging because (i) conventional FL incurs huge training latency for mobile devices due to interleaved local computing and communications of model updates, (ii) there are heterogeneous training data across mobile devices, and (iii) mobile devices have hardware heterogeneity in terms of computing and communication capabilities.
no code implementations • 29 Nov 2021 • Tian Liu, Zhiwei Ling, Jun Xia, Xin Fu, Shui Yu, Mingsong Chen
Inspired by Knowledge Distillation (KD) that can increase the model accuracy, our approach adds the soft targets used by KD to the FL model training, which occupies negligible network resources.
no code implementations • 7 Oct 2021 • Qiyu Wan, Haojun Xia, Xingyao Zhang, Lening Wang, Shuaiwen Leon Song, Xin Fu
Bayesian Neural Networks (BNNs) that possess a property of uncertainty estimation have been increasingly adopted in a wide range of safety-critical AI applications which demand reliable and robust decision making, e. g., self-driving, rescue robots, medical image diagnosis.
2 code implementations • 12 May 2021 • Xiongwei Wu, Xin Fu, Ying Liu, Ee-Peng Lim, Steven C. H. Hoi, Qianru Sun
Existing food image segmentation models are underperforming due to two reasons: (1) there is a lack of high quality food image datasets with fine-grained ingredient labels and pixel-wise location masks -- the existing datasets either carry coarse ingredient labels or are small in size; and (2) the complex appearance of food makes it difficult to localize and recognize ingredients in food images, e. g., the ingredients may overlap one another in the same image, and the identical ingredient may appear distinctly in different food images.
Ranked #3 on
Semantic Segmentation
on FoodSeg103
(using extra training data)
no code implementations • 16 Feb 2021 • Jian Jin, Xingxing Zhang, Xin Fu, huan zhang, Weisi Lin, Jian Lou, Yao Zhao
Experimental results on image classification demonstrate that we successfully find the JND for deep machine vision.
no code implementations • 27 Nov 2020 • Xin Fu, Tseleung So, Jongbaek Song
Let $X$ be a $4$-dimensional toric orbifold.
Algebraic Topology Primary 57R18, 55P15, Secondary 55P60
no code implementations • 7 Nov 2019 • Xingyao Zhang, Shuaiwen Leon Song, Chenhao Xie, Jing Wang, Weigong Zhang, Xin Fu
In recent years, the CNNs have achieved great successes in the image processing tasks, e. g., image recognition and object detection.
2 code implementations • 18 Apr 2019 • Jia Yan, Jie Li, Xin Fu
No-reference image quality assessment (NR-IQA) aims to measure the image quality without reference image.
no code implementations • 22 Feb 2019 • Xin Fu, Chengkai Zhang, Xiang Peng, Lihua Jian, Zheng Liu
Pulsed eddy current (PEC) is an effective electromagnetic non-destructive inspection (NDI) technique for metal materials, which has already been widely adopted in detecting cracking and corrosion in some multi-layer structures.
no code implementations • 22 Feb 2019 • Xin Fu, Jia Yan, Cien Fan
Also, we analyzed the factors that could influence the performance from two aspects: the architecture of the deep neural network and the contribution of local and scene-aware information.