Jianyuan Guo

papers

9,502

total citations

papers (23)

One-for-All: Bridge the Gap Between Heterogeneous Architectures in Knowledge Distillation

NEURIPS 2023arXiv

134

citations

Hire-MLP: Vision MLP via Hierarchical Rearrangement

CVPR 2022arXiv

115

citations

Hit-Detector: Hierarchical Trinity Architecture Search for Object Detection

CVPR 2020arXiv

103

citations

Learning Efficient Vision Transformers via Fine-Grained Manifold Distillation

NEURIPS 2022arXiv

citations

Masked Image Modeling With Local Multi-Scale Reconstruction

CVPR 2023arXiv

citations

GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer

ICML 2024arXiv

citations

Brain-Inspired Multilayer Perceptron With Spiking Neurons

CVPR 2022arXiv

citations

Revisit the Power of Vanilla Knowledge Distillation: from Small Scale to Large Scale

NEURIPS 2023arXiv

citations

HourNAS: Extremely Fast Neural Architecture Search Through an Hourglass Lens

CVPR 2021arXiv

citations

Data-efficient Large Vision Models through Sequential Autoregression

ICML 2024arXiv

citations

A Transformer-Based Object Detector with Coarse-Fine Crossing Representations

NEURIPS 2022

citations

Positive-Unlabeled Data Purification in the Wild for Object Detection

CVPR 2021

citations

ParameterNet: Parameters Are All You Need for Large-scale Visual Pretraining of Mobile Networks

CVPR 2024

citations

Jianyuan Guo

papers (23)

GhostNet: More Features From Cheap Operations

Transformer in Transformer

CMT: Convolutional Neural Networks Meet Vision Transformers

Vision GNN: An Image is Worth Graph of Nodes

GhostNetV2: Enhance Cheap Operation with Long-Range Attention

Gold-YOLO: Efficient Object Detector via Gather-and-Distribute Mechanism

Distilling Object Detectors via Decoupled Features

Patch Slimming for Efficient Vision Transformers

VanillaNet: the Power of Minimalism in Deep Learning

An Image Patch Is a Wave: Phase-Aware Vision MLP

One-for-All: Bridge the Gap Between Heterogeneous Architectures in Knowledge Distillation

Hire-MLP: Vision MLP via Hierarchical Rearrangement

Hit-Detector: Hierarchical Trinity Architecture Search for Object Detection

Learning Efficient Vision Transformers via Fine-Grained Manifold Distillation

Masked Image Modeling With Local Multi-Scale Reconstruction

GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer

Brain-Inspired Multilayer Perceptron With Spiking Neurons

Revisit the Power of Vanilla Knowledge Distillation: from Small Scale to Large Scale

HourNAS: Extremely Fast Neural Architecture Search Through an Hourglass Lens

Data-efficient Large Vision Models through Sequential Autoregression

A Transformer-Based Object Detector with Coarse-Fine Crossing Representations

Positive-Unlabeled Data Purification in the Wild for Object Detection

ParameterNet: Parameters Are All You Need for Large-scale Visual Pretraining of Mobile Networks

papers (23)

GhostNet: More Features From Cheap Operations

Transformer in Transformer

CMT: Convolutional Neural Networks Meet Vision Transformers

Vision GNN: An Image is Worth Graph of Nodes

GhostNetV2: Enhance Cheap Operation with Long-Range Attention

Gold-YOLO: Efficient Object Detector via Gather-and-Distribute Mechanism

Distilling Object Detectors via Decoupled Features

Patch Slimming for Efficient Vision Transformers

VanillaNet: the Power of Minimalism in Deep Learning

An Image Patch Is a Wave: Phase-Aware Vision MLP

One-for-All: Bridge the Gap Between Heterogeneous Architectures in Knowledge Distillation

Hire-MLP: Vision MLP via Hierarchical Rearrangement

Hit-Detector: Hierarchical Trinity Architecture Search for Object Detection

Learning Efficient Vision Transformers via Fine-Grained Manifold Distillation

Masked Image Modeling With Local Multi-Scale Reconstruction

GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer

Brain-Inspired Multilayer Perceptron With Spiking Neurons

Revisit the Power of Vanilla Knowledge Distillation: from Small Scale to Large Scale

HourNAS: Extremely Fast Neural Architecture Search Through an Hourglass Lens

Data-efficient Large Vision Models through Sequential Autoregression

A Transformer-Based Object Detector with Coarse-Fine Crossing Representations

Positive-Unlabeled Data Purification in the Wild for Object Detection

ParameterNet: Parameters Are All You Need for Large-scale Visual Pretraining of Mobile Networks