Yuyin Zhou

papers

1,161

total citations

papers (20)

Multi-Granularity Cross-modal Alignment for Generalized Medical Visual Representation Learning

NEURIPS 2022arXiv

225

citations

Rethinking Architecture Design for Tackling Data Heterogeneity in Federated Learning

CVPR 2022arXiv

217

citations

Universal Physical Camouflage Attacks on Object Detectors

CVPR 2020arXiv

200

citations

Deep Distance Transform for Tubular Structure Segmentation in CT Scans

CVPR 2020arXiv

132

citations

MedTrinity-25M: A Large-scale Multimodal Dataset with Multigranular Annotations for Medicine

ICLR 2025arXiv

citations

Unleashing the Potential of SAM for Medical Adaptation via Hierarchical Decoding

CVPR 2024arXiv

citations

Sculpting Holistic 3D Representation in Contrastive Language-Image-3D Pre-training

CVPR 2024arXiv

citations

L2B: Learning to Bootstrap Robust Models for Combating Label Noise

CVPR 2024arXiv

citations

MicroDiffusion: Implicit Representation-Guided Diffusion for 3D Reconstruction from Limited 2D Microscopy Projections

CVPR 2024arXiv

citations

FLHetBench: Benchmarking Device and State Heterogeneity in Federated Learning

CVPR 2024

citations

A New Federated Learning Framework Against Gradient Inversion Attacks

AAAI 2025arXiv

citations

MedSegFactory: Text-Guided Generation of Medical Image-Mask Pairs

ICCV 2025arXiv

citations

Adventurer: Optimizing Vision Mamba Architecture Designs for Efficiency

CVPR 2025arXiv

citations

In Defense of Image Pre-training for Spatiotemporal Recognition

ECCV 2022arXiv

citations

CD2-pFed: Cyclic Distillation-Guided Channel Decoupling for Model Personalization in Federated Learning

CVPR 2022

citations

Mamba-Reg: Vision Mamba Also Needs Registers

CVPR 2025

citations

Yuyin Zhou

papers (20)

Multi-Granularity Cross-modal Alignment for Generalized Medical Visual Representation Learning

Rethinking Architecture Design for Tackling Data Heterogeneity in Federated Learning

Universal Physical Camouflage Attacks on Object Detectors

Deep Distance Transform for Tubular Structure Segmentation in CT Scans

MedTrinity-25M: A Large-scale Multimodal Dataset with Multigranular Annotations for Medicine

Unleashing the Potential of SAM for Medical Adaptation via Hierarchical Decoding

Masked Autoencoders Enable Efficient Knowledge Distillers

Neural Architecture Search for Lightweight Non-Local Networks

A Simple Data Mixing Prior for Improving Self-Supervised Learning

Generative Image Layer Decomposition with Visual Effects

Sculpting Holistic 3D Representation in Contrastive Language-Image-3D Pre-training

L2B: Learning to Bootstrap Robust Models for Combating Label Noise

MicroDiffusion: Implicit Representation-Guided Diffusion for 3D Reconstruction from Limited 2D Microscopy Projections

FLHetBench: Benchmarking Device and State Heterogeneity in Federated Learning

A New Federated Learning Framework Against Gradient Inversion Attacks

MedSegFactory: Text-Guided Generation of Medical Image-Mask Pairs

Adventurer: Optimizing Vision Mamba Architecture Designs for Efficiency

In Defense of Image Pre-training for Spatiotemporal Recognition

CD2-pFed: Cyclic Distillation-Guided Channel Decoupling for Model Personalization in Federated Learning

Mamba-Reg: Vision Mamba Also Needs Registers

papers (20)

Multi-Granularity Cross-modal Alignment for Generalized Medical Visual Representation Learning

Rethinking Architecture Design for Tackling Data Heterogeneity in Federated Learning

Universal Physical Camouflage Attacks on Object Detectors

Deep Distance Transform for Tubular Structure Segmentation in CT Scans

MedTrinity-25M: A Large-scale Multimodal Dataset with Multigranular Annotations for Medicine

Unleashing the Potential of SAM for Medical Adaptation via Hierarchical Decoding

Masked Autoencoders Enable Efficient Knowledge Distillers

Neural Architecture Search for Lightweight Non-Local Networks

A Simple Data Mixing Prior for Improving Self-Supervised Learning

Generative Image Layer Decomposition with Visual Effects

Sculpting Holistic 3D Representation in Contrastive Language-Image-3D Pre-training

L2B: Learning to Bootstrap Robust Models for Combating Label Noise

MicroDiffusion: Implicit Representation-Guided Diffusion for 3D Reconstruction from Limited 2D Microscopy Projections

FLHetBench: Benchmarking Device and State Heterogeneity in Federated Learning

A New Federated Learning Framework Against Gradient Inversion Attacks

MedSegFactory: Text-Guided Generation of Medical Image-Mask Pairs

Adventurer: Optimizing Vision Mamba Architecture Designs for Efficiency

In Defense of Image Pre-training for Spatiotemporal Recognition

CD2-pFed: Cyclic Distillation-Guided Channel Decoupling for Model Personalization in Federated Learning

Mamba-Reg: Vision Mamba Also Needs Registers