Yifan Sun

papers

1,877

total citations

papers (27)

Circle Loss: A Unified Perspective of Pair Similarity Optimization

CVPR 2020arXiv

981

citations

Deep Representation Learning on Long-Tailed Data: A Learnable Embedding Augmentation Perspective

CVPR 2020arXiv

232

citations

IDM: An Intermediate Domain Module for Domain Adaptive Person Re-ID

ICCV 2021arXiv

141

citations

A Unified Continual Learning Framework with General Parameter-Efficient Tuning

ICCV 2023arXiv

139

citations

CycAs: Self-supervised Cycle Association for Learning Re-identifiable Descriptions

ECCV 2020arXiv

103

citations

Dynamic Metric Learning: Towards a Scalable Metric Space To Accommodate Multiple Semantic Scales

CVPR 2021arXiv

citations

DETR With Additional Global Aggregation for Cross-Domain Weakly Supervised Object Detection

CVPR 2023arXiv

citations

Hyperbolic Space with Hierarchical Margin Boosts Fine-Grained Learning from Coarse Labels

NEURIPS 2023arXiv

citations

UFO: Unified Feature Optimization

ECCV 2022arXiv

citations

Spatial Ensemble: a Novel Model Smoothing Mechanism for Student-Teacher Framework

NEURIPS 2021arXiv

citations

CoST: Efficient Collaborative Perception From Unified Spatiotemporal Perspective

ICCV 2025arXiv

citations

Personalized Bayesian Federated Learning with Wasserstein Barycenter Aggregation

NEURIPS 2025arXiv

citations

Learning View Selection for 3D Scenes

CVPR 2021

citations

Learning Memory-Augmented Unidirectional Metrics for Cross-Modality Person Re-Identification

CVPR 2022

citations

H2FA R-CNN: Holistic and Hierarchical Feature Alignment for Cross-Domain Weakly Supervised Object Detection

CVPR 2022

citations

EASE-DETR: Easing the Competition among Object Queries

CVPR 2024

citations

Pose Synchronization Under Multiple Pair-Wise Relative Poses

CVPR 2023

citations

Regression Learning with Limited Observations of Multivariate Outcomes and Features

ICML 2024

citations

DAC-DETR: Divide the Attention Layers and Conquer

NEURIPS 2023

citations

ProD: Prompting-To-Disentangle Domain Knowledge for Cross-Domain Few-Shot Image Classification

CVPR 2023

citations

Context-Aware Pretraining for Efficient Blind Image Decomposition

CVPR 2023

citations

Absolute Policy Optimization: Enhancing Lower Probability Bound of Performance with High Confidence

ICML 2024

citations

Yifan Sun

papers (27)

Circle Loss: A Unified Perspective of Pair Similarity Optimization

Deep Representation Learning on Long-Tailed Data: A Learnable Embedding Augmentation Perspective

IDM: An Intermediate Domain Module for Domain Adaptive Person Re-ID

A Unified Continual Learning Framework with General Parameter-Efficient Tuning

CycAs: Self-supervised Cycle Association for Learning Re-identifiable Descriptions

Feature-Proxy Transformer for Few-Shot Segmentation

MS-DETR: Efficient DETR Training with Mixed Supervision

Jigsaw: Learning to Assemble Multiple Fractured Objects

Large-Scale Person Detection and Localization Using Overhead Fisheye Cameras

TransHP: Image Classification with Hierarchical Prompting

Dynamic Metric Learning: Towards a Scalable Metric Space To Accommodate Multiple Semantic Scales

DETR With Additional Global Aggregation for Cross-Domain Weakly Supervised Object Detection

Hyperbolic Space with Hierarchical Margin Boosts Fine-Grained Learning from Coarse Labels

UFO: Unified Feature Optimization

Spatial Ensemble: a Novel Model Smoothing Mechanism for Student-Teacher Framework

CoST: Efficient Collaborative Perception From Unified Spatiotemporal Perspective

Personalized Bayesian Federated Learning with Wasserstein Barycenter Aggregation

Learning View Selection for 3D Scenes

Learning Memory-Augmented Unidirectional Metrics for Cross-Modality Person Re-Identification

H2FA R-CNN: Holistic and Hierarchical Feature Alignment for Cross-Domain Weakly Supervised Object Detection

EASE-DETR: Easing the Competition among Object Queries

Pose Synchronization Under Multiple Pair-Wise Relative Poses

Regression Learning with Limited Observations of Multivariate Outcomes and Features

DAC-DETR: Divide the Attention Layers and Conquer

ProD: Prompting-To-Disentangle Domain Knowledge for Cross-Domain Few-Shot Image Classification

Context-Aware Pretraining for Efficient Blind Image Decomposition

Absolute Policy Optimization: Enhancing Lower Probability Bound of Performance with High Confidence

papers (27)

Circle Loss: A Unified Perspective of Pair Similarity Optimization

Deep Representation Learning on Long-Tailed Data: A Learnable Embedding Augmentation Perspective

IDM: An Intermediate Domain Module for Domain Adaptive Person Re-ID

A Unified Continual Learning Framework with General Parameter-Efficient Tuning

CycAs: Self-supervised Cycle Association for Learning Re-identifiable Descriptions

Feature-Proxy Transformer for Few-Shot Segmentation

MS-DETR: Efficient DETR Training with Mixed Supervision

Jigsaw: Learning to Assemble Multiple Fractured Objects

Large-Scale Person Detection and Localization Using Overhead Fisheye Cameras

TransHP: Image Classification with Hierarchical Prompting

Dynamic Metric Learning: Towards a Scalable Metric Space To Accommodate Multiple Semantic Scales

DETR With Additional Global Aggregation for Cross-Domain Weakly Supervised Object Detection

Hyperbolic Space with Hierarchical Margin Boosts Fine-Grained Learning from Coarse Labels

UFO: Unified Feature Optimization

Spatial Ensemble: a Novel Model Smoothing Mechanism for Student-Teacher Framework

CoST: Efficient Collaborative Perception From Unified Spatiotemporal Perspective

Personalized Bayesian Federated Learning with Wasserstein Barycenter Aggregation

Learning View Selection for 3D Scenes

Learning Memory-Augmented Unidirectional Metrics for Cross-Modality Person Re-Identification

H2FA R-CNN: Holistic and Hierarchical Feature Alignment for Cross-Domain Weakly Supervised Object Detection

EASE-DETR: Easing the Competition among Object Queries

Pose Synchronization Under Multiple Pair-Wise Relative Poses

Regression Learning with Limited Observations of Multivariate Outcomes and Features

DAC-DETR: Divide the Attention Layers and Conquer

ProD: Prompting-To-Disentangle Domain Knowledge for Cross-Domain Few-Shot Image Classification

Context-Aware Pretraining for Efficient Blind Image Decomposition

Absolute Policy Optimization: Enhancing Lower Probability Bound of Performance with High Confidence