kyegomez/VisualNexus

An plug in and play pipeline that utilizes segment anything to segment datasets with rich detail for downstream fine-tuning on vision models like CLIP, ViT, Imagebind, and so on!

4 best points · 3 comments · 1 Hacker News post · 20 GitHub stars · View on GitHub

Hacker News discussions

• VisualNexus – Training Pipeline for Visual Dataset Segmentation and Labeling (4 points, 3 comments, by Reclaimer, 2023-06-22)