Explanipedia

SWiFT: Soft-Mask Weight Fine-tuning for Bias Mitigation Open

Junyu Yan, Feng Chen, Yuyang Xue, Yuning Du, Konstantinos Vilouras , et al. · 2025

Recent studies have shown that Machine Learning (ML) models can exhibit bias in real-world scenarios, posing significant challenges in ethically sensitive domains such as healthcare. Such bias can negatively affect model fairness, model ge…

Active Sampling for MRI-based Sequential Decision Making Open

Yuning Du, Jingshuai Liu, Rohan Dharmakumar, Sotirios A. Tsaftaris · 2025

Despite the superior diagnostic capability of Magnetic Resonance Imaging (MRI), its use as a Point-of-Care (PoC) device remains limited by high cost and complexity. To enable such a future by reducing the magnetic field strength, one key a…

The MRI Scanner as a Diagnostic: Image-less Active Sampling Open

Yuning Du, Rohan Dharmakumar, Sotirios A. Tsaftaris · 2024

Despite the high diagnostic accuracy of Magnetic Resonance Imaging (MRI), using MRI as a Point-of-Care (POC) disease identification tool poses significant accessibility challenges due to the use of high magnetic field strength and lengthy …

LRANet: Towards Accurate and Efficient Scene Text Detection with Low-Rank Approximation Network Open

Yuchen Su, Zhineng Chen, Zhiwen Shao, Yuning Du, Zhilong Ji , et al. · 2024

Recently, regression-based methods, which predict parameterized text shapes for text localization, have gained popularity in scene text detection. However, the existing parameterized text shape methods still have limitations in modeling ar…

Unveiling Fairness Biases in Deep Learning-Based Brain MRI Reconstruction Open

Yuning Du, Yuyang Xue, Rohan Dharmakumar, Sotirios A. Tsaftaris · 2023

Deep learning (DL) reconstruction particularly of MRI has led to improvements in image fidelity and reduction of acquisition time. In neuroimaging, DL methods can reconstruct high-quality images from undersampled data. However, it is essen…

Cine cardiac MRI reconstruction using a convolutional recurrent network with refinement Open

Yuyang Xue, Yuning Du, Gianluca Carloni, Eva Pachetti, Connor Jordan , et al. · 2023

Cine Magnetic Resonance Imaging (MRI) allows for understanding of the heart's function and condition in a non-invasive manner. Undersampling of the $k$-space is employed to reduce the scan duration, thus increasing patient comfort and redu…

Context Perception Parallel Decoder for Scene Text Recognition Open

Yongkun Du, Zhineng Chen, Caiyan Jia, Xiaoting Yin, Chenxia Li , et al. · 2023

Scene text recognition (STR) methods have struggled to attain high accuracy and fast inference speed. Autoregressive (AR)-based models implement the recognition in a character-by-character manner, showing superiority in accuracy but with s…

ICDAR 2023 Competition on Structured Text Extraction from Visually-Rich Document Images Open

Wenwen Yu, Chengquan Zhang, Haoyu Cao, Wei Hua, Bohan Li , et al. · 2023

Structured text extraction is one of the most valuable and challenging application directions in the field of Document AI. However, the scenarios of past benchmarks are limited, and the corresponding evaluation protocols usually focus on t…

DETRs Beat YOLOs on Real-time Object Detection Open

Wenyu Lv, Shangliang Xu, Y. Zhao, Guanzhong Wang, Jinman Wei , et al. · 2023

The YOLO series has become the most popular framework for real-time object detection due to its reasonable trade-off between speed and accuracy. However, we observe that the speed and accuracy of YOLOs are negatively affected by the NMS. R…

PP-StructureV2: A Stronger Document Analysis System Open

Chenxia Li, Ruoyu Guo, Jun Zhou, Mengtao An, Yuning Du , et al. · 2022

A large amount of document data exists in unstructured form such as raw images without any text information. Designing a practical document image analysis system is a meaningful but challenging task. In previous work, we proposed an intell…

SVTR: Scene Text Recognition with a Single Visual Model Open

Yongkun Du, Zhineng Chen, Caiyan Jia, Xiaoting Yin, Tianlun Zheng , et al. · 2022

Dominant scene text recognition models commonly contain two building blocks, a visual model for feature extraction and a sequence model for text transcription. This hybrid architecture, although accurate, is complex and less efficient. In …

PP-OCRv3: More Attempts for the Improvement of Ultra Lightweight OCR System Open

Chenxia Li, Weiwei Liu, Ruoyu Guo, Xiaoting Yin, Kaitao Jiang , et al. · 2022

Optical character recognition (OCR) technology has been widely used in various scenes, as shown in Figure 1. Designing a practical OCR system is still a meaningful but challenging task. In previous work, considering the efficiency and accu…

SVTR: Scene Text Recognition with a Single Visual Model Open

Yongkun Du, Zhineng Chen, Caiyan Jia, Xiaoting Yin, Tianlun Zheng , et al. · 2022

Dominant scene text recognition models commonly contain two building blocks, a visual model for feature extraction and a sequence model for text transcription. This hybrid architecture, although accurate, is complex and less efficient. In …

PP-Matting: High-Accuracy Natural Image Matting Open

Guowei Chen, Yi Liu, Jian Wang, Juncai Peng, Yuying Hao , et al. · 2022

Natural image matting is a fundamental and challenging computer vision task. It has many applications in image editing and composition. Recently, deep learning-based approaches have achieved great improvements in image matting. However, mo…

PP-LiteSeg: A Superior Real-Time Semantic Segmentation Model Open

Juncai Peng, Yi Liu, Shiyu Tang, Yuying Hao, Lutao Chu , et al. · 2022

Real-world applications have high demands for semantic segmentation methods. Although semantic segmentation has made remarkable leap-forwards with deep learning, the performance of real-time methods is not satisfactory. In this work, we pr…

PP-YOLOE: An evolved version of YOLO Open

Shangliang Xu, Xinxin Wang, Wenyu Lv, Qinyao Chang, Cheng Cui , et al. · 2022

In this report, we present PP-YOLOE, an industrial state-of-the-art object detector with high performance and friendly deployment. We optimize on the basis of the previous PP-YOLOv2, using anchor-free paradigm, more powerful backbone and n…

PP-ShiTu: A Practical Lightweight Image Recognition System Open

Shengyu Wei, Ruoyu Guo, Cheng Cui, Bin Lü, Shuilong Dong , et al. · 2021

In recent years, image recognition applications have developed rapidly. A large number of studies and techniques have emerged in different fields, such as face recognition, pedestrian and vehicle re-identification, landmark retrieval, and …

PP-PicoDet: A Better Real-Time Object Detector on Mobile Devices Open

Guanghua Yu, Qinyao Chang, Wenyu Lv, Chang Xu, Cheng Cui , et al. · 2021

The better accuracy and efficiency trade-off has been a challenging problem in object detection. In this work, we are dedicated to studying key optimizations and neural network architecture choices for object detection to improve accuracy …

PP-LCNet: A Lightweight CPU Convolutional Neural Network Open

Cheng Cui, Tingquan Gao, Shengyu Wei, Yuning Du, Ruoyu Guo , et al. · 2021

We propose a lightweight CPU network based on the MKLDNN acceleration strategy, named PP-LCNet, which improves the performance of lightweight models on multiple tasks. This paper lists technologies which can improve network accuracy while …

PP-OCRv2: Bag of Tricks for Ultra Lightweight OCR System Open

Yuning Du, Chenxia Li, Ruoyu Guo, Cheng Cui, Weiwei Liu , et al. · 2021

Optical Character Recognition (OCR) systems have been widely used in various of application scenarios. Designing an OCR system is still a challenging task. In previous work, we proposed a practical ultra lightweight OCR system (PP-OCR) to …

Beyond Self-Supervision: A Simple Yet Effective Network Distillation Alternative to Improve Backbones Open

Cheng Cui, Ruoyu Guo, Yuning Du, Dongliang He, Fu Li , et al. · 2021

Recently, research efforts have been concentrated on revealing how pre-trained model makes a difference in neural network performance. Self-supervision and semi-supervised learning technologies have been extensively explored by the communi…

HS-ResNet: Hierarchical-Split Block on Convolutional Neural Network Open

Pengcheng Yuan, Shufei Lin, Cheng Cui, Yuning Du, Ruoyu Guo , et al. · 2020

This paper addresses representational block named Hierarchical-Split Block, which can be taken as a plug-and-play block to upgrade existing convolutional neural networks, improves model performance significantly in a network. Hierarchical-…

PP-OCR: A Practical Ultra Lightweight OCR System Open

Yuning Du, Chenxia Li, Ruoyu Guo, Xiaoting Yin, Weiwei Liu , et al. · 2020

The Optical Character Recognition (OCR) systems have been widely used in various of application scenarios, such as office automation (OA) systems, factory automations, online educations, map productions etc. However, OCR is still a challen…

2nd Place Solution in Google AI Open Images Object Detection Track 2019 Open

Ruoyu Guo, Cheng Cui, Yuning Du, Xianglong Meng, Xiaodi Wang , et al. · 2019

We present an object detection framework based on PaddlePaddle. We put all the strategies together (multi-scale training, FPN, Cascade, Dcnv2, Non-local, libra loss) based on ResNet200-vd backbone. Our model score on public leaderboard com…

2nd Place and 2nd Place Solution to Kaggle Landmark Recognition andRetrieval Competition 2019 Open

Kaibing Chen, Cheng Cui, Yuning Du, Xianglong Meng, Hui Ren · 2019

We present a retrieval based system for landmark retrieval and recognition challenge.There are five parts in retrieval competition system, including feature extraction and matching to get candidates queue; database augmentation and query e…

Yuning Du YOU? Author Swipe