Yinpeng Chen

papers

4,252

total citations

papers (24)

Masked Video Distillation: Rethinking Masked Feature Modeling for Self-Supervised Video Representation Learning

CVPR 2023arXiv

121

citations

MicroNet: Improving Image Recognition With Extremely Low FLOPs

ICCV 2021arXiv

104

citations

Reduce Information Loss in Transformers for Pluralistic Image Inpainting

CVPR 2022arXiv

citations

Dynamic Transfer for Multi-Source Domain Adaptation

CVPR 2021arXiv

citations

Stronger NAS with Weaker Predictors

NEURIPS 2021arXiv

citations

Detection Hub: Unifying Object Detection Datasets via Query Adaptation on Language Embedding

CVPR 2023arXiv

citations

DA-NAS: Data Adapted Pruning for Efficient Neural Architecture Search

ECCV 2020arXiv

citations

Improve Unsupervised Pretraining for Few-Label Transfer

ICCV 2021arXiv

citations

Learning from Rich Semantics and Coarse Locations for Long-tailed Object Detection

NEURIPS 2023arXiv

citations

Improving Adversarial Robustness of Masked Autoencoders via Test-time Frequency-domain Prompting

ICCV 2023arXiv

citations

Auto-Linear Phenomenon in Subsurface Imaging

ICML 2024arXiv

citations

Should All Proposals Be Treated Equally in Object Detection?

ECCV 2022arXiv

citations

Completing Visual Objects via Bridging Generation and Segmentation

ICML 2024arXiv

citations

Exploring Invariance in Images through One-way Wave Equations

ICML 2025arXiv

citations

Dynamic DETR: End-to-End Object Detection With Dynamic Attention

ICCV 2021

citations

PaintSeg: Painting Pixels for Training-free Segmentation

NEURIPS 2023

citations

OpenFWI: Large-scale Multi-structural Benchmark Datasets for Full Waveform Inversion

NEURIPS 2022

citations

$\mathbf{\mathbb{E}^{FWI}}$: Multiparameter Benchmark Datasets for Elastic Full Waveform Inversion of Geophysical Properties

NEURIPS 2023

citations

Yinpeng Chen

papers (24)

Dynamic Convolution: Attention Over Convolution Kernels

Dynamic Head: Unifying Object Detection Heads With Attentions

Mobile-Former: Bridging MobileNet and Transformer

Rethinking Classification and Localization for Object Detection

BEVT: BERT Pretraining of Video Transformers

Dynamic ReLU

Masked Video Distillation: Rethinking Masked Feature Modeling for Self-Supervised Video Representation Learning

MicroNet: Improving Image Recognition With Extremely Low FLOPs

Reduce Information Loss in Transformers for Pluralistic Image Inpainting

Dynamic Transfer for Multi-Source Domain Adaptation

Stronger NAS with Weaker Predictors

Detection Hub: Unifying Object Detection Datasets via Query Adaptation on Language Embedding

DA-NAS: Data Adapted Pruning for Efficient Neural Architecture Search

Improve Unsupervised Pretraining for Few-Label Transfer

Learning from Rich Semantics and Coarse Locations for Long-tailed Object Detection

Improving Adversarial Robustness of Masked Autoencoders via Test-time Frequency-domain Prompting

Auto-Linear Phenomenon in Subsurface Imaging

Should All Proposals Be Treated Equally in Object Detection?

Completing Visual Objects via Bridging Generation and Segmentation

Exploring Invariance in Images through One-way Wave Equations

Dynamic DETR: End-to-End Object Detection With Dynamic Attention

PaintSeg: Painting Pixels for Training-free Segmentation

OpenFWI: Large-scale Multi-structural Benchmark Datasets for Full Waveform Inversion

$\mathbf{\mathbb{E}^{FWI}}$: Multiparameter Benchmark Datasets for Elastic Full Waveform Inversion of Geophysical Properties

papers (24)

Dynamic Convolution: Attention Over Convolution Kernels

Dynamic Head: Unifying Object Detection Heads With Attentions

Mobile-Former: Bridging MobileNet and Transformer

Rethinking Classification and Localization for Object Detection

BEVT: BERT Pretraining of Video Transformers

Dynamic ReLU

Masked Video Distillation: Rethinking Masked Feature Modeling for Self-Supervised Video Representation Learning

MicroNet: Improving Image Recognition With Extremely Low FLOPs

Reduce Information Loss in Transformers for Pluralistic Image Inpainting

Dynamic Transfer for Multi-Source Domain Adaptation

Stronger NAS with Weaker Predictors

Detection Hub: Unifying Object Detection Datasets via Query Adaptation on Language Embedding

DA-NAS: Data Adapted Pruning for Efficient Neural Architecture Search

Improve Unsupervised Pretraining for Few-Label Transfer

Learning from Rich Semantics and Coarse Locations for Long-tailed Object Detection

Improving Adversarial Robustness of Masked Autoencoders via Test-time Frequency-domain Prompting

Auto-Linear Phenomenon in Subsurface Imaging

Should All Proposals Be Treated Equally in Object Detection?

Completing Visual Objects via Bridging Generation and Segmentation

Exploring Invariance in Images through One-way Wave Equations

Dynamic DETR: End-to-End Object Detection With Dynamic Attention

PaintSeg: Painting Pixels for Training-free Segmentation

OpenFWI: Large-scale Multi-structural Benchmark Datasets for Full Waveform Inversion

$\mathbf{\mathbb{E}^{FWI}}$: Multiparameter Benchmark Datasets for Elastic Full Waveform Inversion of Geophysical Properties