Search Results for author: Xin Fu

Found 9 papers, 2 papers with code

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 #2 on Semantic Segmentation on FoodSeg103 (using extra training data)

Semantic Segmentation

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.

object-detection Object Detection +1

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 SSIM

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

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

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