Benchmarking Vision-Language Models on Synapse Detection and Proofreading in Connectomics
When evaluated on unseen species, the best adapted VLMs outperformed specialist models trained on the same data in identifying merge errors and LoRA on a few thousand labels brought open models level with specialist models.
Yi-Cong Li, Jun-Jie Wang, Leander Lauenburg et al.
· 0 citations