Search Results for author: Xin Fu

Found 12 papers, 2 papers with code

DEDGAT: Dual Embedding of Directed Graph Attention Networks for Detecting Financial Risk

no code implementations6 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.

Graph Attention

CyclicFL: A Cyclic Model Pre-Training Approach to Efficient Federated Learning

no code implementations28 Jan 2023 Pengyu Zhang, Yingbo Zhou, Ming Hu, Xin Fu, Xian Wei, Mingsong Chen

Based on the concept of Continual Learning (CL), we prove that CyclicFL approximates existing centralized pre-training methods in terms of classification and prediction performance.

Continual Learning Federated Learning

Workie-Talkie: Accelerating Federated Learning by Overlapping Computing and Communications via Contrastive Regularization

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.

Federated Learning

Efficient Federated Learning for AIoT Applications Using Knowledge Distillation

no code implementations29 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.

Federated Learning Knowledge Distillation

Shift-BNN: Highly-Efficient Probabilistic Bayesian Neural Network Training via Memory-Friendly Pattern Retrieving

no code implementations7 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.

Decision Making

A Large-Scale Benchmark for Food Image Segmentation

2 code implementations12 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)

Image Segmentation Segmentation +1

Just Noticeable Difference for Deep Machine Vision

no code implementations16 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.

Image Classification Neural Network Security +1

The homotopy classification of four-dimensional toric orbifolds

no code implementations27 Nov 2020 Xin Fu, Tseleung So, Jongbaek Song

Let $X$ be a $4$-dimensional toric orbifold.

Algebraic Topology Primary 57R18, 55P15, Secondary 55P60

Enabling Highly Efficient Capsule Networks Processing Through A PIM-Based Architecture Design

no code implementations7 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.

Image Segmentation object-detection +2

No-Reference Quality Assessment of Contrast-Distorted Images using Contrast Enhancement

2 code implementations18 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-Reference Image Quality Assessment NR-IQA +1

Towards end-to-end pulsed eddy current classification and regression with CNN

no code implementations22 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.

General Classification regression

Image Aesthetics Assessment Using Composite Features from off-the-Shelf Deep Models

no code implementations22 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.

Image Classification Scene Recognition

Cannot find the paper you are looking for? You can Submit a new open access paper.