Junsong Fan

papers

181

total citations

papers (12)

DDG-Net: Discriminability-Driven Graph Network for Weakly-supervised Temporal Action Localization

ICCV 2023arXiv

citations

General Geometry-aware Weakly Supervised 3D Object Detection

ECCV 2024arXiv

citations

Point-supervised Panoptic Segmentation via Estimating Pseudo Labels from Learnable Distance

ECCV 2024

citations

Learning Integral Objects With Intra-Class Discriminator for Weakly-Supervised Semantic Segmentation

CVPR 2020

citations

Towards Noiseless Object Contours for Weakly Supervised Semantic Segmentation

CVPR 2022

citations

Remember the Difference: Cross-Domain Few-Shot Semantic Segmentation via Meta-Memory Transfer

CVPR 2022

citations

Employing Multi-Estimations for Weakly-Supervised Semantic Segmentation

ECCV 2020

citations

Fully Data-Driven Pseudo Label Estimation for Pointly-Supervised Panoptic Segmentation

AAAI 2024

citations

Junsong Fan

papers (12)

Hard Patches Mining for Masked Image Modeling

Pointly-Supervised Panoptic Segmentation

DropPos: Pre-Training Vision Transformers by Reconstructing Dropped Positions

Continual Forgetting for Pre-trained Vision Models

DDG-Net: Discriminability-Driven Graph Network for Weakly-supervised Temporal Action Localization

General Geometry-aware Weakly Supervised 3D Object Detection

Point-supervised Panoptic Segmentation via Estimating Pseudo Labels from Learnable Distance

Learning Integral Objects With Intra-Class Discriminator for Weakly-Supervised Semantic Segmentation

Towards Noiseless Object Contours for Weakly Supervised Semantic Segmentation

Remember the Difference: Cross-Domain Few-Shot Semantic Segmentation via Meta-Memory Transfer

Employing Multi-Estimations for Weakly-Supervised Semantic Segmentation

Fully Data-Driven Pseudo Label Estimation for Pointly-Supervised Panoptic Segmentation

papers (12)

Hard Patches Mining for Masked Image Modeling

Pointly-Supervised Panoptic Segmentation

DropPos: Pre-Training Vision Transformers by Reconstructing Dropped Positions

Continual Forgetting for Pre-trained Vision Models

DDG-Net: Discriminability-Driven Graph Network for Weakly-supervised Temporal Action Localization

General Geometry-aware Weakly Supervised 3D Object Detection

Point-supervised Panoptic Segmentation via Estimating Pseudo Labels from Learnable Distance

Learning Integral Objects With Intra-Class Discriminator for Weakly-Supervised Semantic Segmentation

Towards Noiseless Object Contours for Weakly Supervised Semantic Segmentation

Remember the Difference: Cross-Domain Few-Shot Semantic Segmentation via Meta-Memory Transfer

Employing Multi-Estimations for Weakly-Supervised Semantic Segmentation

Fully Data-Driven Pseudo Label Estimation for Pointly-Supervised Panoptic Segmentation