Search Results for author: Yinghuan Shi

Found 70 papers, 38 papers with code

Constructing and Exploring Intermediate Domains in Mixed Domain Semi-supervised Medical Image Segmentation

1 code implementation13 Apr 2024 Qinghe Ma, Jian Zhang, Lei Qi, Qian Yu, Yinghuan Shi, Yang Gao

To fully utilize the information within the intermediate domain, we propose a symmetric Guidance training strategy (SymGD), which additionally offers direct guidance to unlabeled data by merging pseudo labels from intermediate samples.

Image Segmentation Segmentation +4

SETA: Semantic-Aware Token Augmentation for Domain Generalization

1 code implementation18 Mar 2024 Jintao Guo, Lei Qi, Yinghuan Shi, Yang Gao

In this paper, we study the impact of prior CNN-based augmentation methods on token-based models, revealing their performance is suboptimal due to the lack of incentivizing the model to learn holistic shape information.

Data Augmentation Domain Generalization

Concatenate, Fine-tuning, Re-training: A SAM-enabled Framework for Semi-supervised 3D Medical Image Segmentation

1 code implementation17 Mar 2024 Shumeng Li, Lei Qi, Qian Yu, Jing Huo, Yinghuan Shi, Yang Gao

Segment Anything Model (SAM) fine-tuning has shown remarkable performance in medical image segmentation in a fully supervised manner, but requires precise annotations.

Image Segmentation Segmentation +2

Learning Generalizable Models via Disentangling Spurious and Enhancing Potential Correlations

1 code implementation11 Jan 2024 Na Wang, Lei Qi, Jintao Guo, Yinghuan Shi, Yang Gao

2) From the feature perspective, the simple Tail Interaction module implicitly enhances potential correlations among all samples from all source domains, facilitating the acquisition of domain-invariant representations across multiple domains for the model.

Data Augmentation Domain Generalization

PG-LBO: Enhancing High-Dimensional Bayesian Optimization with Pseudo-Label and Gaussian Process Guidance

1 code implementation28 Dec 2023 Taicai Chen, Yue Duan, Dong Li, Lei Qi, Yinghuan Shi, Yang Gao

Based on this technique, we assign appropriate training weights to unlabeled data to enhance the construction of a discriminative latent space.

Bayesian Optimization Pseudo Label

Roll With the Punches: Expansion and Shrinkage of Soft Label Selection for Semi-supervised Fine-Grained Learning

1 code implementation19 Dec 2023 Yue Duan, Zhen Zhao, Lei Qi, Luping Zhou, Lei Wang, Yinghuan Shi

While semi-supervised learning (SSL) has yielded promising results, the more realistic SSL scenario remains to be explored, in which the unlabeled data exhibits extremely high recognition difficulty, e. g., fine-grained visual classification in the context of SSL (SS-FGVC).

Fine-Grained Image Classification Pseudo Label

Exploring Flat Minima for Domain Generalization with Large Learning Rates

no code implementations12 Sep 2023 Jian Zhang, Lei Qi, Yinghuan Shi, Yang Gao

Instead, we observe that leveraging a large learning rate can simultaneously promote weight diversity and facilitate the identification of flat regions in the loss landscape.

Domain Generalization Semantic Segmentation

Enhancing Sample Utilization through Sample Adaptive Augmentation in Semi-Supervised Learning

1 code implementation ICCV 2023 Guan Gui, Zhen Zhao, Lei Qi, Luping Zhou, Lei Wang, Yinghuan Shi

Sample adaptive augmentation (SAA) is proposed for this stated purpose and consists of two modules: 1) sample selection module; 2) sample augmentation module.

A Theoretical Explanation of Activation Sparsity through Flat Minima and Adversarial Robustness

no code implementations6 Sep 2023 Ze Peng, Lei Qi, Yinghuan Shi, Yang Gao

Although having attributed it to training dynamics, existing theoretical explanations of activation sparsity are restricted to shallow networks, small training steps and special training, despite its emergence in deep models standardly trained for a large number of steps.

DomainAdaptor: A Novel Approach to Test-time Adaptation

1 code implementation ICCV 2023 Jian Zhang, Lei Qi, Yinghuan Shi, Yang Gao

To deal with the domain shift between training and test samples, current methods have primarily focused on learning generalizable features during training and ignore the specificity of unseen samples that are also critical during the test.

Specificity Test-time Adaptation

Generalizable Decision Boundaries: Dualistic Meta-Learning for Open Set Domain Generalization

1 code implementation ICCV 2023 Xiran Wang, Jian Zhang, Lei Qi, Yinghuan Shi

Domain generalization (DG) is proposed to deal with the issue of domain shift, which occurs when statistical differences exist between source and target domains.

Domain Generalization Meta-Learning

A Novel Cross-Perturbation for Single Domain Generalization

no code implementations2 Aug 2023 Dongjia Zhao, Lei Qi, Xiao Shi, Yinghuan Shi, Xin Geng

Horizontally, it applies image-level and feature-level perturbations to enhance the diversity of the training data, mitigating the issue of limited diversity in single-source domains.

Domain Generalization

3D Medical Image Segmentation with Sparse Annotation via Cross-Teaching between 3D and 2D Networks

1 code implementation30 Jul 2023 Heng Cai, Lei Qi, Qian Yu, Yinghuan Shi, Yang Gao

Our experimental results on the MMWHS dataset demonstrate that our method outperforms the state-of-the-art (SOTA) semi-supervised segmentation methods.

Image Segmentation Medical Image Segmentation +3

Generalizable Metric Network for Cross-domain Person Re-identification

no code implementations21 Jun 2023 Lei Qi, Ziang Liu, Yinghuan Shi, Xin Geng

Additionally, we introduce the Dropout-based Perturbation (DP) module to enhance the generalization capability of the metric network by enriching the sample-pair diversity.

Domain Generalization Person Re-Identification

Patch-aware Batch Normalization for Improving Cross-domain Robustness

no code implementations6 Apr 2023 Lei Qi, Dongjia Zhao, Yinghuan Shi, Xin Geng

By exploiting the differences between local patches of an image, our proposed PBN can effectively enhance the robustness of the model's parameters.

Data Augmentation object-detection +3

Orthogonal Annotation Benefits Barely-supervised Medical Image Segmentation

1 code implementation CVPR 2023 Heng Cai, Shumeng Li, Lei Qi, Qian Yu, Yinghuan Shi, Yang Gao

Subsequently, by introducing unlabeled volumes, we propose a dual-network paradigm named Dense-Sparse Co-training (DeSCO) that exploits dense pseudo labels in early stage and sparse labels in later stage and meanwhile forces consistent output of two networks.

Image Segmentation Semantic Segmentation +1

ALOFT: A Lightweight MLP-like Architecture with Dynamic Low-frequency Transform for Domain Generalization

1 code implementation CVPR 2023 Jintao Guo, Na Wang, Lei Qi, Yinghuan Shi

However, the local operation of the convolution kernel makes the model focus too much on local representations (e. g., texture), which inherently causes the model more prone to overfit to the source domains and hampers its generalization ability.

Domain Generalization

PLN: Parasitic-Like Network for Barely Supervised Medical Image Segmentation

1 code implementation IEEE Transactions on Medical Imaging 2022 Shumeng Li, Heng Cai; Lei Qi, Qian Yu, Yinghuan Shi, Yang Gao

In this paper, by introducing an extremely sparse annotation way of labeling only one slice per 3D image, we investigate a novel barely-supervised segmentation setting with only a few sparsely-labeled images along with a large amount of unlabeled images.

Image Segmentation Medical Image Segmentation +2

Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation

1 code implementation CVPR 2023 Lihe Yang, Lei Qi, Litong Feng, Wayne Zhang, Yinghuan Shi

In this work, we revisit the weak-to-strong consistency framework, popularized by FixMatch from semi-supervised classification, where the prediction of a weakly perturbed image serves as supervision for its strongly perturbed version.

Semi-supervised Change Detection Semi-supervised Medical Image Segmentation +1

MultiMatch: Multi-task Learning for Semi-supervised Domain Generalization

no code implementations11 Aug 2022 Lei Qi, Hongpeng Yang, Yinghuan Shi, Xin Geng

To address the task, we first analyze the theory of the multi-domain learning, which highlights that 1) mitigating the impact of domain gap and 2) exploiting all samples to train the model can effectively reduce the generalization error in each source domain so as to improve the quality of pseudo-labels.

Domain Generalization Multi-Task Learning +2

RDA: Reciprocal Distribution Alignment for Robust Semi-supervised Learning

3 code implementations9 Aug 2022 Yue Duan, Lei Qi, Lei Wang, Luping Zhou, Yinghuan Shi

In this work, we propose Reciprocal Distribution Alignment (RDA) to address semi-supervised learning (SSL), which is a hyperparameter-free framework that is independent of confidence threshold and works with both the matched (conventionally) and the mismatched class distributions.

Semi-Supervised Image Classification

Generalizable Medical Image Segmentation via Random Amplitude Mixup and Domain-Specific Image Restoration

1 code implementation8 Aug 2022 Ziqi Zhou, Lei Qi, Yinghuan Shi

We demonstrate the performance of our method on two public generalizable segmentation benchmarks in medical images, which validates our method could achieve the state-of-the-art performance.

Image Restoration Image Segmentation +3

Label Distribution Learning for Generalizable Multi-source Person Re-identification

no code implementations12 Apr 2022 Lei Qi, Jiaying Shen, Jiaqi Liu, Yinghuan Shi, Xin Geng

Besides, for the label distribution of each class, we further revise it to give more and equal attention to the other domains that the class does not belong to, which can effectively reduce the domain gap across different domains and obtain the domain-invariant feature.

Person Re-Identification

MutexMatch: Semi-Supervised Learning with Mutex-Based Consistency Regularization

3 code implementations27 Mar 2022 Yue Duan, Zhen Zhao, Lei Qi, Lei Wang, Luping Zhou, Yinghuan Shi, Yang Gao

The core issue in semi-supervised learning (SSL) lies in how to effectively leverage unlabeled data, whereas most existing methods tend to put a great emphasis on the utilization of high-confidence samples yet seldom fully explore the usage of low-confidence samples.

Semi-Supervised Image Classification

A Novel Mix-normalization Method for Generalizable Multi-source Person Re-identification

no code implementations24 Jan 2022 Lei Qi, Lei Wang, Yinghuan Shi, Xin Geng

Different from the conventional data augmentation, the proposed domain-aware mix-normalization to enhance the diversity of features during training from the normalization view of the neural network, which can effectively alleviate the model overfitting to the source domains, so as to boost the generalization capability of the model in the unseen domain.

Data Augmentation Person Re-Identification

MVDG: A Unified Multi-view Framework for Domain Generalization

1 code implementation23 Dec 2021 Jian Zhang, Lei Qi, Yinghuan Shi, Yang Gao

Beyond the training stage, overfitting could also cause unstable prediction in the test stage.

Domain Generalization Meta-Learning

Generalizable Cross-modality Medical Image Segmentation via Style Augmentation and Dual Normalization

1 code implementation CVPR 2022 Ziqi Zhou, Lei Qi, Xin Yang, Dong Ni, Yinghuan Shi

For medical image segmentation, imagine if a model was only trained using MR images in source domain, how about its performance to directly segment CT images in target domain?

Domain Generalization Image Segmentation +3

PLACE dropout: A Progressive Layer-wise and Channel-wise Dropout for Domain Generalization

1 code implementation7 Dec 2021 Jintao Guo, Lei Qi, Yinghuan Shi, Yang Gao

Particularly, the proposed method can generate a variety of data variants to better deal with the overfitting issue.

Domain Generalization

Unsupervised Domain Generalization for Person Re-identification: A Domain-specific Adaptive Framework

1 code implementation30 Nov 2021 Lei Qi, Jiaqi Liu, Lei Wang, Yinghuan Shi, Xin Geng

A significance of our work lies in that it shows the potential of unsupervised domain generalization for person ReID and sets a strong baseline for the further research on this topic.

Domain Generalization Person Re-Identification +1

Inconsistency-aware Uncertainty Estimation for Semi-supervised Medical Image Segmentation

1 code implementation17 Oct 2021 Yinghuan Shi, Jian Zhang, Tong Ling, Jiwen Lu, Yefeng Zheng, Qian Yu, Lei Qi, Yang Gao

In semi-supervised medical image segmentation, most previous works draw on the common assumption that higher entropy means higher uncertainty.

Image Segmentation Segmentation +2

Better Pseudo-label: Joint Domain-aware Label and Dual-classifier for Semi-supervised Domain Generalization

no code implementations10 Oct 2021 Ruiqi Wang, Lei Qi, Yinghuan Shi, Yang Gao

Also, considering inconsistent goals between generalization and pseudo-labeling: former prevents overfitting on all source domains while latter might overfit the unlabeled source domains for high accuracy, we employ a dual-classifier to independently perform pseudo-labeling and domain generalization in the training process.

Domain Generalization Pseudo Label +1

LibFewShot: A Comprehensive Library for Few-shot Learning

1 code implementation10 Sep 2021 Wenbin Li, Ziyi, Wang, Xuesong Yang, Chuanqi Dong, Pinzhuo Tian, Tiexin Qin, Jing Huo, Yinghuan Shi, Lei Wang, Yang Gao, Jiebo Luo

Furthermore, based on LibFewShot, we provide comprehensive evaluations on multiple benchmarks with various backbone architectures to evaluate common pitfalls and effects of different training tricks.

Data Augmentation Few-Shot Image Classification +2

Crosslink-Net: Double-branch Encoder Segmentation Network via Fusing Vertical and Horizontal Convolutions

1 code implementation24 Jul 2021 Qian Yu, Lei Qi, Luping Zhou, Lei Wang, Yilong Yin, Yinghuan Shi, Wuzhang Wang, Yang Gao

Together, the above two schemes give rise to a novel double-branch encoder segmentation framework for medical image segmentation, namely Crosslink-Net.

Image Segmentation Medical Image Segmentation +2

ST++: Make Self-training Work Better for Semi-supervised Semantic Segmentation

1 code implementation CVPR 2022 Lihe Yang, Wei Zhuo, Lei Qi, Yinghuan Shi, Yang Gao

In this work, we first construct a strong baseline of self-training (namely ST) for semi-supervised semantic segmentation via injecting strong data augmentations (SDA) on unlabeled images to alleviate overfitting noisy labels as well as decouple similar predictions between the teacher and student.

Semi-Supervised Semantic Segmentation

Feature-based Style Randomization for Domain Generalization

no code implementations6 Jun 2021 Yue Wang, Lei Qi, Yinghuan Shi, Yang Gao

As a recent noticeable topic, domain generalization (DG) aims to first learn a generic model on multiple source domains and then directly generalize to an arbitrary unseen target domain without any additional adaption.

Data Augmentation Domain Generalization

Deep Symmetric Adaptation Network for Cross-modality Medical Image Segmentation

no code implementations18 Jan 2021 Xiaoting Han, Lei Qi, Qian Yu, Ziqi Zhou, Yefeng Zheng, Yinghuan Shi, Yang Gao

These typical methods usually utilize a translation network to transform images from the source domain to target domain or train the pixel-level classifier merely using translated source images and original target images.

Image Segmentation Medical Image Segmentation +4

Learning-based Computer-aided Prescription Model for Parkinson's Disease: A Data-driven Perspective

no code implementations31 Jul 2020 Yinghuan Shi, Wanqi Yang, Kim-Han Thung, Hao Wang, Yang Gao, Yang Pan, Li Zhang, Dinggang Shen

Then, we build a novel computer-aided prescription model by learning the relation between observed symptoms and prescription drug.

Manifold Alignment for Semantically Aligned Style Transfer

1 code implementation ICCV 2021 Jing Huo, Shiyin Jin, Wenbin Li, Jing Wu, Yu-Kun Lai, Yinghuan Shi, Yang Gao

In this paper, we make a new assumption that image features from the same semantic region form a manifold and an image with multiple semantic regions follows a multi-manifold distribution.

Semantic Segmentation Style Transfer

Class Distribution Alignment for Adversarial Domain Adaptation

no code implementations20 Apr 2020 Wanqi Yang, Tong Ling, Chengmei Yang, Lei Wang, Yinghuan Shi, Luping Zhou, Ming Yang

To address this issue, we propose a novel approach called Conditional ADversarial Image Translation (CADIT) to explicitly align the class distributions given samples between the two domains.

General Classification Translation +1

Diversity Helps: Unsupervised Few-shot Learning via Distribution Shift-based Data Augmentation

1 code implementation13 Apr 2020 Tiexin Qin, Wenbin Li, Yinghuan Shi, Yang Gao

Importantly, we highlight the value and importance of the distribution diversity in the augmentation-based pretext few-shot tasks, which can effectively alleviate the overfitting problem and make the few-shot model learn more robust feature representations.

Data Augmentation Unsupervised Few-Shot Image Classification +1

Review of Artificial Intelligence Techniques in Imaging Data Acquisition, Segmentation and Diagnosis for COVID-19

1 code implementation6 Apr 2020 Feng Shi, Jun Wang, Jun Shi, Ziyan Wu, Qian Wang, Zhenyu Tang, Kelei He, Yinghuan Shi, Dinggang Shen

In this review paper, we thus cover the entire pipeline of medical imaging and analysis techniques involved with COVID-19, including image acquisition, segmentation, diagnosis, and follow-up.

Computed Tomography (CT)

Crossover-Net: Leveraging the Vertical-Horizontal Crossover Relation for Robust Segmentation

no code implementations3 Apr 2020 Qian Yu, Yinghuan Shi, Yefeng Zheng, Yang Gao, Jianbing Zhu, Yakang Dai

Robust segmentation for non-elongated tissues in medical images is hard to realize due to the large variation of the shape, size, and appearance of these tissues in different patients.

Relation Segmentation

Generalizable Model-agnostic Semantic Segmentation via Target-specific Normalization

1 code implementation27 Mar 2020 Jian Zhang, Lei Qi, Yinghuan Shi, Yang Gao

Semantic segmentation in a supervised learning manner has achieved significant progress in recent years.

Domain Generalization Segmentation +1

Automatic Data Augmentation via Deep Reinforcement Learning for Effective Kidney Tumor Segmentation

no code implementations22 Feb 2020 Tiexin Qin, Ziyuan Wang, Kelei He, Yinghuan Shi, Yang Gao, Dinggang Shen

Conventional data augmentation realized by performing simple pre-processing operations (\eg, rotation, crop, \etc) has been validated for its advantage in enhancing the performance for medical image segmentation.

Data Augmentation Image Segmentation +5

Asymmetric Distribution Measure for Few-shot Learning

no code implementations1 Feb 2020 Wenbin Li, Lei Wang, Jing Huo, Yinghuan Shi, Yang Gao, Jiebo Luo

Given the natural asymmetric relation between a query image and a support class, we argue that an asymmetric measure is more suitable for metric-based few-shot learning.

Few-Shot Image Classification Few-Shot Learning

Differentiable Meta-learning Model for Few-shot Semantic Segmentation

no code implementations23 Nov 2019 Pinzhuo Tian, Zhangkai Wu, Lei Qi, Lei Wang, Yinghuan Shi, Yang Gao

To address the annotation scarcity issue in some cases of semantic segmentation, there have been a few attempts to develop the segmentation model in the few-shot learning paradigm.

Few-Shot Semantic Segmentation Object +2

Automatic Data Augmentation by Learning the Deterministic Policy

1 code implementation18 Oct 2019 Yinghuan Shi, Tiexin Qin, Yong liu, Jiwen Lu, Yang Gao, Dinggang Shen

By introducing an unified optimization goal, DeepAugNet intends to combine the data augmentation and the deep model training in an end-to-end training manner which is realized by simultaneously training a hybrid architecture of dueling deep Q-learning algorithm and a surrogate deep model.

Data Augmentation Q-Learning

Progressive Cross-camera Soft-label Learning for Semi-supervised Person Re-identification

no code implementations15 Aug 2019 Lei Qi, Lei Wang, Jing Huo, Yinghuan Shi, Yang Gao

In this paper, we focus on the semi-supervised person re-identification (Re-ID) case, which only has the intra-camera (within-camera) labels but not inter-camera (cross-camera) labels.

Semi-Supervised Person Re-Identification

GreyReID: A Two-stream Deep Framework with RGB-grey Information for Person Re-identification

no code implementations14 Aug 2019 Lei Qi, Lei Wang, Jing Huo, Yinghuan Shi, Yang Gao

Moreover, in the training process, we adopt the joint learning scheme to simultaneously train each branch by the independent loss function, which can enhance the generalization ability of each branch.

Person Re-Identification

Adversarial Camera Alignment Network for Unsupervised Cross-camera Person Re-identification

no code implementations2 Aug 2019 Lei Qi, Lei Wang, Jing Huo, Yinghuan Shi, Xin Geng, Yang Gao

To achieve the camera alignment, we develop a Multi-Camera Adversarial Learning (MCAL) to map images of different cameras into a shared subspace.

Person Re-Identification

A Novel Unsupervised Camera-aware Domain Adaptation Framework for Person Re-identification

no code implementations ICCV 2019 Lei Qi, Lei Wang, Jing Huo, Luping Zhou, Yinghuan Shi, Yang Gao

For the first issue, we highlight the presence of camera-level sub-domains as a unique characteristic of person Re-ID, and develop camera-aware domain adaptation to reduce the discrepancy not only between source and target domains but also across these sub-domains.

Person Re-Identification Representation Learning +1

A Multilayer Framework for Online Metric Learning

1 code implementation15 May 2018 Wenbin Li, Yanfang Liu, Jing Huo, Yinghuan Shi, Yang Gao, Lei Wang, Jiebo Luo

Furthermore, in a progressively and nonlinearly learning way, MLOML has a stronger learning ability than traditional online metric learning in the case of limited available training data.

Metric Learning

Crossbar-Net: A Novel Convolutional Network for Kidney Tumor Segmentation in CT Images

no code implementations27 Apr 2018 Qian Yu, Yinghuan Shi, Jinquan Sun, Yang Gao, Yakang Dai, Jianbing Zhu

Due to the irregular motion, similar appearance and diverse shape, accurate segmentation of kidney tumor in CT images is a difficult and challenging task.

Cardiac Segmentation Segmentation +1

MaskReID: A Mask Based Deep Ranking Neural Network for Person Re-identification

no code implementations11 Apr 2018 Lei Qi, Jing Huo, Lei Wang, Yinghuan Shi, Yang Gao

Lastly, considering person retrieval is a special image retrieval task, we propose a novel ranking loss to optimize the whole network.

Image Retrieval Person Re-Identification +2

The Automatic Identification of Butterfly Species

no code implementations18 Mar 2018 Juanying Xie, Qi Hou, Yinghuan Shi, Lv Peng, Liping Jing, Fuzhen Zhuang, Junping Zhang, Xiaoyang Tang, Shengquan Xu

We delete those species with only one living environment image from data set, then partition the rest images from living environment into two subsets, one used as test subset, the other as training subset respectively combined with all standard pattern butterfly images or the standard pattern butterfly images with the same species of the images from living environment.

Revisiting Metric Learning for SPD Matrix Based Visual Representation

no code implementations CVPR 2017 Luping Zhou, Lei Wang, Jianjia Zhang, Yinghuan Shi, Yang Gao

The proposed method has been tested on multiple SPD-based visual representation data sets used in the literature, and the results demonstrate its interesting properties and attractive performance.

Metric Learning

WebCaricature: a benchmark for caricature recognition

no code implementations9 Mar 2017 Jing Huo, Wenbin Li, Yinghuan Shi, Yang Gao, Hujun Yin

In this paper, a new caricature dataset is built, with the objective to facilitate research in caricature recognition.

Caricature Face Recognition

OPML: A One-Pass Closed-Form Solution for Online Metric Learning

no code implementations29 Sep 2016 Wenbin Li, Yang Gao, Lei Wang, Luping Zhou, Jing Huo, Yinghuan Shi

To achieve a low computational cost when performing online metric learning for large-scale data, we present a one-pass closed-form solution namely OPML in this paper.

Event Detection Face Verification +1

Joint Coupled-Feature Representation and Coupled Boosting for AD Diagnosis

no code implementations CVPR 2014 Yinghuan Shi, Heung-Il Suk, Yang Gao, Dinggang Shen

Therefore, it is natural to hypothesize that the low-level features extracted from neuroimaging data are related to each other in some ways.

Prostate Segmentation in CT Images via Spatial-Constrained Transductive Lasso

no code implementations CVPR 2013 Yinghuan Shi, Shu Liao, Yaozong Gao, Daoqiang Zhang, Yang Gao, Dinggang Shen

Specifically, to segment the prostate in the current treatment image, the physician first takes a few seconds to manually specify the first and last slices of the prostate in the image space.


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