Search Results for author: Yongchao Xu

Found 43 papers, 34 papers with code

Intra-class Feature Variation Distillation for Semantic Segmentation

1 code implementation ECCV 2020 Yukang Wang, Wei Zhou, Tao Jiang, Xiang Bai, Yongchao Xu

In this paper, different from previous methods performing knowledge distillation for densely pairwise relations, we propose a novel intra-class feature variation distillation (IFVD) to transfer the intra-class feature variation (IFV) of the cumbersome model (teacher) to the compact model (student).

Knowledge Distillation Segmentation +1

Rejoining fragmented ancient bamboo slips with physics-driven deep learning

1 code implementation13 May 2025 Jinchi Zhu, Zhou Zhao, Hailong Lei, Xiaoguang Wang, Jialiang Lu, Jing Li, Qianqian Tang, Jiachen Shen, Gui-Song Xia, Bo Du, Yongchao Xu

This approach enables the training of a matching network without requiring manually paired samples, providing ranked suggestions to facilitate the rejoining process.

LiftFeat: 3D Geometry-Aware Local Feature Matching

1 code implementation6 May 2025 Yepeng Liu, Wenpeng Lai, Zhou Zhao, Yuxuan Xiong, Jinchi Zhu, Jun Cheng, Yongchao Xu

We then design a 3D geometry-aware feature lifting module to fuse surface normal feature with raw 2D descriptor feature.

3D geometry Homography Estimation +3

CQ-DINO: Mitigating Gradient Dilution via Category Queries for Vast Vocabulary Object Detection

1 code implementation24 Mar 2025 Zhichao Sun, Huazhang Hu, Yidong Ma, Gang Liu, Nemo Chen, Xu Tang, Yao Hu, Yongchao Xu

To address these challenges, we propose CQ-DINO, a category query-based object detection framework that reformulates classification as a contrastive task between object queries and learnable category queries.

Object object-detection +1

Consistent-Point: Consistent Pseudo-Points for Semi-Supervised Crowd Counting and Localization

no code implementations16 Mar 2025 Yuda Zou, Zelong Liu, Yuliang Gu, Bo Du, Yongchao Xu

Crowd counting and localization are important in applications such as public security and traffic management.

Crowd Counting Management

Pathological Prior-Guided Multiple Instance Learning For Mitigating Catastrophic Forgetting in Breast Cancer Whole Slide Image Classification

no code implementations8 Mar 2025 Weixi Zheng, Aoling Huang. Jingping Yuan, Haoyu Zhao, Zhou Zhao, Yongchao Xu, Thierry Géraud

Secondly, it trains separate classification heads for each task and uses macroscopic pathological prior knowledge, treating the thumbnail as a prompt guide (PG) to select the appropriate classification head.

Continual Learning Diagnostic +3

MIFNet: Learning Modality-Invariant Features for Generalizable Multimodal Image Matching

no code implementations20 Jan 2025 Yepeng Liu, Zhichao Sun, Baosheng Yu, Yitian Zhao, Bo Du, Yongchao Xu, Jun Cheng

Extending such methods to multimodal image matching often requires well-aligned multimodal data to learn modality-invariant descriptors.

Keypoint Detection Zero-shot Generalization

CellSeg1: Robust Cell Segmentation with One Training Image

1 code implementation2 Dec 2024 Peilin Zhou, Bo Du, Yongchao Xu

We introduce CellSeg1, a practical solution for segmenting cells of arbitrary morphology and modality with a few dozen cell annotations in 1 image.

Cell Segmentation Segmentation

Shape Transformation Driven by Active Contour for Class-Imbalanced Semi-Supervised Medical Image Segmentation

1 code implementation18 Oct 2024 Yuliang Gu, Yepeng Liu, Zhichao Sun, Jinchi Zhu, Yongchao Xu, Laurent Najman

The significant size differences among various organs in the human body lead to imbalanced class distribution, which is a major challenge in the real-world application of these SSL approaches.

Data Augmentation Image Segmentation +2

Shape-intensity knowledge distillation for robust medical image segmentation

1 code implementation26 Sep 2024 Wenhui Dong, Bo Du, Yongchao Xu

In this paper, we propose a novel approach to incorporate joint shape-intensity prior information into the segmentation network.

Image Segmentation Knowledge Distillation +3

Prompting Segment Anything Model with Domain-Adaptive Prototype for Generalizable Medical Image Segmentation

1 code implementation19 Sep 2024 Zhikai Wei, Wenhui Dong, Peilin Zhou, Yuliang Gu, Zhou Zhao, Yongchao Xu

In this paper, we propose a novel Domain-Adaptive Prompt framework for fine-tuning the Segment Anything Model (termed as DAPSAM) to address single-source domain generalization (SDG) in segmenting medical images.

Image Segmentation Medical Image Segmentation +4

Progressive Retinal Image Registration via Global and Local Deformable Transformations

1 code implementation2 Sep 2024 Yepeng Liu, Baosheng Yu, Tian Chen, Yuliang Gu, Bo Du, Yongchao Xu, Jun Cheng

For that, we use a keypoint detector and a deformation network called GAMorph to estimate the global transformation and local deformable transformation, respectively.

Image Registration

Spatial-aware Attention Generative Adversarial Network for Semi-supervised Anomaly Detection in Medical Image

1 code implementation21 May 2024 Zerui Zhang, Zhichao Sun, Zelong Liu, Bo Du, Rui Yu, Zhou Zhao, Yongchao Xu

Medical anomaly detection is a critical research area aimed at recognizing abnormal images to aid in diagnosis. Most existing methods adopt synthetic anomalies and image restoration on normal samples to detect anomaly.

Generative Adversarial Network Image Restoration +2

Development of Skip Connection in Deep Neural Networks for Computer Vision and Medical Image Analysis: A Survey

1 code implementation2 May 2024 Guoping Xu, Xiaxia Wang, Xinglong Wu, Xuesong Leng, Yongchao Xu

Deep learning has made significant progress in computer vision, specifically in image classification, object detection, and semantic segmentation.

Image Classification Image Reconstruction +5

MoreStyle: Relax Low-frequency Constraint of Fourier-based Image Reconstruction in Generalizable Medical Image Segmentation

1 code implementation18 Mar 2024 Haoyu Zhao, Wenhui Dong, Rui Yu, Zhou Zhao, Du Bo, Yongchao Xu

The task of single-source domain generalization (SDG) in medical image segmentation is crucial due to frequent domain shifts in clinical image datasets.

Data Augmentation Image Reconstruction +4

WIA-LD2ND: Wavelet-based Image Alignment for Self-supervised Low-Dose CT Denoising

1 code implementation18 Mar 2024 Haoyu Zhao, Yuliang Gu, Zhou Zhao, Bo Du, Yongchao Xu, Rui Yu

Second, to better capture high-frequency components and detailed information, Frequency-Aware Multi-scale Loss (FAM) is proposed by effectively utilizing multi-scale feature space.

Image Denoising

Dual Structure-Aware Image Filterings for Semi-supervised Medical Image Segmentation

no code implementations12 Dec 2023 Yuliang Gu, Zhichao Sun, Tian Chen, Xin Xiao, Yepeng Liu, Yongchao Xu, Laurent Najman

In this paper, we propose novel dual structure-aware image filterings (DSAIF) as the image-level variations for semi-supervised medical image segmentation.

Image Segmentation Segmentation +2

Scale-aware Test-time Click Adaptation for Pulmonary Nodule and Mass Segmentation

1 code implementation28 Jul 2023 Zhihao LI, Jiancheng Yang, Yongchao Xu, Li Zhang, Wenhui Dong, Bo Du

Extensive experiments on both open-source and in-house datasets consistently demonstrate the effectiveness of the proposed method over some CNN and Transformer-based segmentation methods.

Image Segmentation Management +4

Not All Pixels Are Equal: Learning Pixel Hardness for Semantic Segmentation

1 code implementation15 May 2023 Xin Xiao, Daiguo Zhou, Jiagao Hu, Yi Hu, Yongchao Xu

Yet, most existing hard pixel mining strategies for semantic segmentation often rely on pixel's loss value, which tends to decrease during training.

All object-detection +3

Scratch Each Other's Back: Incomplete Multi-Modal Brain Tumor Segmentation via Category Aware Group Self-Support Learning

1 code implementation ICCV 2023 Yansheng Qiu, Delin Chen, Hongdou Yao, Yongchao Xu, Zheng Wang

In this paper, considering the sensitivity of different modalities to diverse tumor regions, we propose a Category Aware Group Self-Support Learning framework, called GSS, to make up for the information deficit among the modalities in the individual modal feature extraction phase.

Brain Tumor Segmentation Tumor Segmentation

Local Intensity Order Transformation for Robust Curvilinear Object Segmentation

1 code implementation25 Feb 2022 Tianyi Shi, Nicolas Boutry, Yongchao Xu, Thierry Géraud

This results in a representation that preserves the inherent characteristic of the curvilinear structure while being robust to contrast changes.

Crack Segmentation Object +1

Affinity Space Adaptation for Semantic Segmentation Across Domains

1 code implementation26 Sep 2020 Wei Zhou, Yukang Wang, Jiajia Chu, Jiehua Yang, Xiang Bai, Yongchao Xu

Specifically, we perform domain adaptation on the affinity relationship between adjacent pixels termed affinity space of source and target domain.

Segmentation Semantic Segmentation +1

Learning Directional Feature Maps for Cardiac MRI Segmentation

1 code implementation22 Jul 2020 Feng Cheng, Cheng Chen, Yukang Wang, Heshui Shi, Yukun Cao, Dandan Tu, Changzheng Zhang, Yongchao Xu

Cardiac MRI segmentation plays a crucial role in clinical diagnosis for evaluating personalized cardiac performance parameters.

Cardiac Segmentation MRI segmentation +1

Super-BPD: Super Boundary-to-Pixel Direction for Fast Image Segmentation

1 code implementation CVPR 2020 Jianqiang Wan, Yang Liu, Donglai Wei, Xiang Bai, Yongchao Xu

In this paper, we propose a fast image segmentation method based on a novel super boundary-to-pixel direction (super-BPD) and a customized segmentation algorithm with super-BPD.

Image Segmentation Segmentation +2

AutoSTR: Efficient Backbone Search for Scene Text Recognition

2 code implementations ECCV 2020 Hui Zhang, Quanming Yao, Mingkun Yang, Yongchao Xu, Xiang Bai

In this work, inspired by the success of neural architecture search (NAS), which can identify better architectures than human-designed ones, we propose automated STR (AutoSTR) to search data-dependent backbones to boost text recognition performance.

Deblurring Diversity +2

AutoScale: Learning to Scale for Crowd Counting and Localization

2 code implementations20 Dec 2019 Chenfeng Xu, Dingkang Liang, Yongchao Xu, Song Bai, Wei Zhan, Xiang Bai, Masayoshi Tomizuka

A major issue is that the density map on dense regions usually accumulates density values from a number of nearby Gaussian blobs, yielding different large density values on a small set of pixels.

Crowd Counting Model Optimization

All You Need Is Boundary: Toward Arbitrary-Shaped Text Spotting

no code implementations21 Nov 2019 Hao Wang, Pu Lu, HUI ZHANG, Mingkun Yang, Xiang Bai, Yongchao Xu, Mengchao He, Yongpan Wang, Wenyu Liu

Recently, end-to-end text spotting that aims to detect and recognize text from cluttered images simultaneously has received particularly growing interest in computer vision.

All Instance Segmentation +4

Gliding vertex on the horizontal bounding box for multi-oriented object detection

1 code implementation21 Nov 2019 Yongchao Xu, Mingtao Fu, Qimeng Wang, Yukang Wang, Kai Chen, Gui-Song Xia, Xiang Bai

Yet, the widely adopted horizontal bounding box representation is not appropriate for ubiquitous oriented objects such as objects in aerial images and scene texts.

Ranked #48 on Object Detection In Aerial Images on DOTA (using extra training data)

Object object-detection +5

Learn to Scale: Generating Multipolar Normalized Density Maps for Crowd Counting

no code implementations ICCV 2019 Chenfeng Xu, Kai Qiu, Jianlong Fu, Song Bai, Yongchao Xu, Xiang Bai

Dense crowd counting aims to predict thousands of human instances from an image, by calculating integrals of a density map over image pixels.

Crowd Counting Density Estimation

TextField: Learning A Deep Direction Field for Irregular Scene Text Detection

1 code implementation4 Dec 2018 Yongchao Xu, Yukang Wang, Wei Zhou, Yongpan Wang, Zhibo Yang, Xiang Bai

Experimental results show that the proposed TextField outperforms the state-of-the-art methods by a large margin (28% and 8%) on two curved text datasets: Total-Text and CTW1500, respectively, and also achieves very competitive performance on multi-oriented datasets: ICDAR 2015 and MSRA-TD500.

Scene Text Detection Text Detection

DeepFlux for Skeletons in the Wild

2 code implementations CVPR 2019 Yukang Wang, Yongchao Xu, Stavros Tsogkas, Xiang Bai, Sven Dickinson, Kaleem Siddiqi

In the present article, we depart from this strategy by training a CNN to predict a two-dimensional vector field, which maps each scene point to a candidate skeleton pixel, in the spirit of flux-based skeletonization algorithms.

Edge Detection Object +3

Hard-Aware Point-to-Set Deep Metric for Person Re-identification

1 code implementation ECCV 2018 Rui Yu, Zhiyong Dou, Song Bai, Zhao-Xiang Zhang, Yongchao Xu, Xiang Bai

Person re-identification (re-ID) is a highly challenging task due to large variations of pose, viewpoint, illumination, and occlusion.

Metric Learning Person Re-Identification +1

Deep-Person: Learning Discriminative Deep Features for Person Re-Identification

1 code implementation29 Nov 2017 Xiang Bai, Mingkun Yang, Tengteng Huang, Zhiyong Dou, Rui Yu, Yongchao Xu

Recently, many methods of person re-identification (Re-ID) rely on part-based feature representation to learn a discriminative pedestrian descriptor.

Person Re-Identification Re-Ranking

Integrating Scene Text and Visual Appearance for Fine-Grained Image Classification

no code implementations15 Apr 2017 Xiang Bai, Mingkun Yang, Pengyuan Lyu, Yongchao Xu, Jiebo Luo

Then, we combine the word embedding of the recognized words and the deep visual features into a single representation, which is optimized by a convolutional neural network for fine-grained image classification.

Classification Fine-Grained Image Classification +2

Hierarchical image simplification and segmentation based on Mumford-Shah-salient level line selection

no code implementations15 Mar 2016 Yongchao Xu, Thierry Géraud, Laurent Najman

Many image simplification and segmentation methods are driven by the optimization of an energy functional, for instance the celebrated Mumford-Shah functional.

Attribute Segmentation

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