← Search

Shengtao Lou

1 accepted papers

2024

MaskFactory: Towards High-quality Synthetic Data Generation for Dichotomous Image Segmentation

NeurIPS 2024poster

Dichotomous Image Segmentation (DIS) tasks require highly precise annotations, and traditional dataset creation methods are labor intensive, costly, and require extensive domain expertise. Although using synthetic data for DIS is a promising solution to these challenges, current generative models an…