Search Results for author: Tao Song

Found 27 papers, 18 papers with code

CGI-DM: Digital Copyright Authentication for Diffusion Models via Contrasting Gradient Inversion

no code implementations17 Mar 2024 Xiaoyu Wu, Yang Hua, Chumeng Liang, Jiaru Zhang, Hao Wang, Tao Song, Haibing Guan

In response, we present Contrasting Gradient Inversion for Diffusion Models (CGI-DM), a novel method featuring vivid visual representations for digital copyright authentication.

Image Generation

SkyMask: Attack-agnostic Robust Federated Learning with Fine-grained Learnable Masks

no code implementations19 Dec 2023 Peishen Yan, Hao Wang, Tao Song, Yang Hua, Ruhui Ma, Ningxin Hu, Mohammad R. Haghighat, Haibing Guan

Specifically, the FL server applies parameter-level masks to model updates uploaded by clients and trains the masks over a small clean dataset (i. e., root dataset) to learn the subtle difference between benign and malicious model updates in a high-dimension space.

Federated Learning

PFLlib: Personalized Federated Learning Algorithm Library

1 code implementation8 Dec 2023 Jianqing Zhang, Yang Liu, Yang Hua, Hao Wang, Tao Song, Zhengui Xue, Ruhui Ma, Jian Cao

Amid the ongoing advancements in Federated Learning (FL), a machine learning paradigm that allows collaborative learning with data privacy protection, personalized FL (pFL) has gained significant prominence as a research direction within the FL domain.

Personalized Federated Learning

MD-IQA: Learning Multi-scale Distributed Image Quality Assessment with Semi Supervised Learning for Low Dose CT

no code implementations14 Nov 2023 Tao Song, Ruizhi Hou, Lisong Dai, Lei Xiang

Image quality assessment (IQA) plays a critical role in optimizing radiation dose and developing novel medical imaging techniques in computed tomography (CT).

Computed Tomography (CT) Image Quality Assessment

FedCP: Separating Feature Information for Personalized Federated Learning via Conditional Policy

3 code implementations1 Jul 2023 Jianqing Zhang, Yang Hua, Hao Wang, Tao Song, Zhengui Xue, Ruhui Ma, Haibing Guan

To address this, we propose the Federated Conditional Policy (FedCP) method, which generates a conditional policy for each sample to separate the global information and personalized information in its features and then processes them by a global head and a personalized head, respectively.

Personalized Federated Learning

Adversarial Example Does Good: Preventing Painting Imitation from Diffusion Models via Adversarial Examples

1 code implementation9 Feb 2023 Chumeng Liang, Xiaoyu Wu, Yang Hua, Jiaru Zhang, Yiming Xue, Tao Song, Zhengui Xue, Ruhui Ma, Haibing Guan

Recently, Diffusion Models (DMs) boost a wave in AI for Art yet raise new copyright concerns, where infringers benefit from using unauthorized paintings to train DMs to generate novel paintings in a similar style.

FedALA: Adaptive Local Aggregation for Personalized Federated Learning

2 code implementations2 Dec 2022 Jianqing Zhang, Yang Hua, Hao Wang, Tao Song, Zhengui Xue, Ruhui Ma, Haibing Guan

A key challenge in federated learning (FL) is the statistical heterogeneity that impairs the generalization of the global model on each client.

Personalized Federated Learning

Contrastive Semi-supervised Learning for Domain Adaptive Segmentation Across Similar Anatomical Structures

1 code implementation18 Aug 2022 Ran Gu, Jingyang Zhang, Guotai Wang, Wenhui Lei, Tao Song, Xiaofan Zhang, Kang Li, Shaoting Zhang

To solve this problem, we propose Contrastive Semi-supervised learning for Cross Anatomy Domain Adaptation (CS-CADA) that adapts a model to segment similar structures in a target domain, which requires only limited annotations in the target domain by leveraging a set of existing annotated images of similar structures in a source domain.

Anatomy Contrastive Learning +4

Semi-Supervised Medical Image Segmentation via Cross Teaching between CNN and Transformer

1 code implementation9 Dec 2021 Xiangde Luo, Minhao Hu, Tao Song, Guotai Wang, Shaoting Zhang

Notably, this work may be the first attempt to combine CNN and transformer for semi-supervised medical image segmentation and achieve promising results on a public benchmark.

Image Segmentation Pseudo Label +3

WORD: A large scale dataset, benchmark and clinical applicable study for abdominal organ segmentation from CT image

4 code implementations3 Nov 2021 Xiangde Luo, Wenjun Liao, Jianghong Xiao, Jieneng Chen, Tao Song, Xiaofan Zhang, Kang Li, Dimitris N. Metaxas, Guotai Wang, Shaoting Zhang

Deep learning-based medical image segmentation has shown the potential to reduce manual delineation efforts, but it still requires a large-scale fine annotated dataset for training, and there is a lack of large-scale datasets covering the whole abdomen region with accurate and detailed annotations for the whole abdominal organ segmentation.

Image Segmentation Medical Image Segmentation +4

Robust Bayesian Neural Networks by Spectral Expectation Bound Regularization

1 code implementation CVPR 2021 Jiaru Zhang, Yang Hua, Zhengui Xue, Tao Song, Chengyu Zheng, Ruhui Ma, Haibing Guan

Bayesian neural networks have been widely used in many applications because of the distinctive probabilistic representation framework.

Fast and Accurate Scene Parsing via Bi-direction Alignment Networks

1 code implementation25 May 2021 Yanran Wu, Xiangtai Li, Chen Shi, Yunhai Tong, Yang Hua, Tao Song, Ruhui Ma, Haibing Guan

Motivated by this, we propose a novel network by aligning two-path information into each other through a learned flow field.

Scene Parsing

MIDeepSeg: Minimally Interactive Segmentation of Unseen Objects from Medical Images Using Deep Learning

2 code implementations25 Apr 2021 Xiangde Luo, Guotai Wang, Tao Song, Jingyang Zhang, Michael Aertsen, Jan Deprest, Sebastien Ourselin, Tom Vercauteren, Shaoting Zhang

To solve these problems, we propose a novel deep learning-based interactive segmentation method that not only has high efficiency due to only requiring clicks as user inputs but also generalizes well to a range of previously unseen objects.

Image Segmentation Interactive Segmentation +3

SCPM-Net: An Anchor-free 3D Lung Nodule Detection Network using Sphere Representation and Center Points Matching

1 code implementation12 Apr 2021 Xiangde Luo, Tao Song, Guotai Wang, Jieneng Chen, Yinan Chen, Kang Li, Dimitris N. Metaxas, Shaoting Zhang

To overcome these problems, we propose a 3D sphere representation-based center-points matching detection network that is anchor-free and automatically predicts the position, radius, and offset of nodules without the manual design of nodule/anchor parameters.

Lung Nodule Detection

Self-Supervised Vessel Segmentation via Adversarial Learning

1 code implementation ICCV 2021 Yuxin Ma, Yang Hua, Hanming Deng, Tao Song, Hao Wang, Zhengui Xue, Heng Cao, Ruhui Ma, Haibing Guan

Vessel segmentation is critically essential for diagnosinga series of diseases, e. g., coronary artery disease and retinal disease.

Domain Adaptation Segmentation

Efficient Semi-Supervised Gross Target Volume of Nasopharyngeal Carcinoma Segmentation via Uncertainty Rectified Pyramid Consistency

2 code implementations13 Dec 2020 Xiangde Luo, Wenjun Liao, Jieneng Chen, Tao Song, Yinan Chen, Shichuan Zhang, Nianyong Chen, Guotai Wang, Shaoting Zhang

In this paper, we propose a novel framework with Uncertainty Rectified Pyramid Consistency (URPC) regularization for semi-supervised NPC GTV segmentation.

Segmentation

CA-Net: Comprehensive Attention Convolutional Neural Networks for Explainable Medical Image Segmentation

3 code implementations22 Sep 2020 Ran Gu, Guotai Wang, Tao Song, Rui Huang, Michael Aertsen, Jan Deprest, Sébastien Ourselin, Tom Vercauteren, Shaoting Zhang

Also, we propose a scale attention module implicitly emphasizing the most salient feature maps among multiple scales so that the CNN is adaptive to the size of an object.

Image Segmentation Lesion Segmentation +3

Semi-supervised Medical Image Segmentation through Dual-task Consistency

1 code implementation9 Sep 2020 Xiangde Luo, Jieneng Chen, Tao Song, Yinan Chen, Guotai Wang, Shaoting Zhang

Concretely, we use a dual-task deep network that jointly predicts a pixel-wise segmentation map and a geometry-aware level set representation of the target.

Image Segmentation Segmentation +2

Automatic Ischemic Stroke Lesion Segmentation from Computed Tomography Perfusion Images by Image Synthesis and Attention-Based Deep Neural Networks

no code implementations7 Jul 2020 Guotai Wang, Tao Song, Qiang Dong, Mei Cui, Ning Huang, Shaoting Zhang

Experimental results showed that our framework achieved the top performance on ISLES 2018 challenge and: 1) our method using synthesized pseudo DWI outperformed methods segmenting the lesion from perfusion parameter maps directly; 2) the feature extractor exploiting additional spatiotemporal CTA images led to better synthesized pseudo DWI quality and higher segmentation accuracy; and 3) the proposed loss functions and network structure improved the pseudo DWI synthesis and lesion segmentation performance.

Image Generation Ischemic Stroke Lesion Segmentation +2

KLDivNet: An unsupervised neural network for multi-modality image registration

no code implementations23 Aug 2019 Yechong Huang, Tao Song, Jiahang Xu, Yinan Chen, Xiahai Zhuang

We then embed the KLDivNet into a registration network to achieve the unsupervised deformable registration for multi-modality images.

Image Registration Medical Image Registration

Generative Model-Based Ischemic Stroke Lesion Segmentation

no code implementations6 Jun 2019 Tao Song

In this paper, we propose a novel generative modelbased segmentation framework composed of an extractor, a generator and a segmentor for ischemic stroke lesion segmentation.

Image Segmentation Ischemic Stroke Lesion Segmentation +3

Small-scale Pedestrian Detection Based on Topological Line Localization and Temporal Feature Aggregation

no code implementations ECCV 2018 Tao Song, Leiyu Sun, Di Xie, Haiming Sun, ShiLiang Pu

A critical issue in pedestrian detection is to detect small-scale objects that will introduce feeble contrast and motion blur in images and videos, which in our opinion should partially resort to deep-rooted annotation bias.

Pedestrian Detection

Small-scale Pedestrian Detection Based on Somatic Topology Localization and Temporal Feature Aggregation

no code implementations4 Jul 2018 Tao Song, Leiyu Sun, Di Xie, Haiming Sun, ShiLiang Pu

A critical issue in pedestrian detection is to detect small-scale objects that will introduce feeble contrast and motion blur in images and videos, which in our opinion should partially resort to deep-rooted annotation bias.

Pedestrian Detection

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