Yutong Lin

papers

34,754

total citations

papers (15)

Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning

CVPR 2021arXiv

454

citations

Negative Margin Matters: Understanding Margin in Few-shot Classification

ECCV 2020arXiv

369

citations

A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-Language Model

ECCV 2022arXiv

295

citations

On Data Scaling in Masked Image Modeling

CVPR 2023arXiv

citations

Parametric Instance Classification for Unsupervised Visual Feature learning

NEURIPS 2020arXiv

citations

V-DETR: DETR with Vertex Relative Position Encoding for 3D Object Detection

ICLR 2024arXiv

citations

Bootstrap Your Object Detector via Mixed Training

NEURIPS 2021arXiv

citations

AugDETR: Improving Multi-scale Learning for Detection Transformer

ECCV 2024

citations

DAMap: Distance-aware MapNet for High Quality HD Map Construction

ICCV 2025arXiv

citations

"A Simple Approach and Benchmark for 21,000-Category Object Detection"

ECCV 2022

citations

Could Giant Pre-trained Image Models Extract Universal Representations?

NEURIPS 2022

citations

DETR Does Not Need Multi-Scale or Locality Design

ICCV 2023

citations

Yutong Lin

papers (15)

Swin Transformer: Hierarchical Vision Transformer Using Shifted Windows

Swin Transformer V2: Scaling Up Capacity and Resolution

SimMIM: A Simple Framework for Masked Image Modeling

Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning

Negative Margin Matters: Understanding Margin in Few-shot Classification

A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-Language Model

On Data Scaling in Masked Image Modeling

Parametric Instance Classification for Unsupervised Visual Feature learning

V-DETR: DETR with Vertex Relative Position Encoding for 3D Object Detection

Bootstrap Your Object Detector via Mixed Training

AugDETR: Improving Multi-scale Learning for Detection Transformer

DAMap: Distance-aware MapNet for High Quality HD Map Construction

"A Simple Approach and Benchmark for 21,000-Category Object Detection"

Could Giant Pre-trained Image Models Extract Universal Representations?

DETR Does Not Need Multi-Scale or Locality Design

papers (15)

Swin Transformer: Hierarchical Vision Transformer Using Shifted Windows

Swin Transformer V2: Scaling Up Capacity and Resolution

SimMIM: A Simple Framework for Masked Image Modeling

Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning

Negative Margin Matters: Understanding Margin in Few-shot Classification

A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-Language Model

On Data Scaling in Masked Image Modeling

Parametric Instance Classification for Unsupervised Visual Feature learning

V-DETR: DETR with Vertex Relative Position Encoding for 3D Object Detection

Bootstrap Your Object Detector via Mixed Training

AugDETR: Improving Multi-scale Learning for Detection Transformer

DAMap: Distance-aware MapNet for High Quality HD Map Construction

"A Simple Approach and Benchmark for 21,000-Category Object Detection"

Could Giant Pre-trained Image Models Extract Universal Representations?

DETR Does Not Need Multi-Scale or Locality Design