OrdinalCLIP

anchor

Findings

• IC-192CLIP's contrastive image-text training objective hinders its ability to rank or order images, yielding near-chance performance on ranking tasks in both zero-shot and fine-tuned settings [compared-to]
• IC-532PLIP's zero-shot encoders produce random-guessing-level survival predictions and consistently underperform CONCH on pathology survival analysis [eval]