DatologyAI
/

cls-opt-vit-b-32

Zero-Shot Image Classification

zero-shot-classification

Model card Files Files and versions

Nano1337 commited on Jun 9, 2025

Commit

aa94d75

·

verified ·

1 Parent(s): e9914e9

Update README.md

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -102,10 +102,10 @@ The model was trained on 13B image-text (multi-epoch) curated from the **DataCom
 ### Zero-shot Classification Performance
-| Benchmark | DatologyAI | SigLIP2 | MetaCLIP | DFN |
-|-----------|------------|---------|----------|-----|
-| ImageNet1k | **76.91%** | 74.0% | 67.5% | 72.1% |
-| ImageNetv2 | **70.2%** | 67.1% | 60.4% | 65.7% |
 ### Training Efficiency
 - Matches SigLIP2 performance with only **5B samples** (87.5% compute reduction)

 ### Zero-shot Classification Performance
+| Benchmark | DatologyAI | SigLIP2 | MetaCLIP |
+|-----------|------------|---------|----------|
+| ImageNet1k | **76.91%** | 74.0% | 67.7% |
+| ImageNetv2 | **70.2%** | 67.1% | 60.4% |
 ### Training Efficiency
 - Matches SigLIP2 performance with only **5B samples** (87.5% compute reduction)