OpenCLIP

anchor

Findings

• IC-147CLIP's OOD performance on rendition domains is largely an artifact of domain contamination in its web-scale training data [primary]
• 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 [eval]
• IC-789CLIP retrieval quality in zero-shot compositional image retrieval scales log-linearly with model size from approximately 150M to 2.5B parameters [primary]