← Search

Peijun Ye

3 accepted papers

2025

Unlearning the Noisy Correspondence Makes CLIP More Robust

ICCV 2025poster

The data appetite for Vision-Language Models (VLMs) has continuously scaled up from the early millions to billions today, which faces an untenable trade-off with data quality and inevitably introduces Noisy Correspondence (NC) samples. Undoubtedly, such semantically unrelated data significantly impa…

2021

SCF-Net: Learning Spatial Contextual Features for Large-Scale Point Cloud Segmentation

CVPR 2021poster

How to learn effective features from large-scale point clouds for semantic segmentation has attracted increasing attention in recent years. Addressing this problem, we propose a learnable module that learns Spatial Contextual Features from large-scale point clouds, called SCF in this paper. The prop…

Cited by 303PDFcodeScholar