Modelpedia
Work in progress
About
Findings
Models
Concepts
Methods
Datasets
Sources
Light
Dark
Caltech-256
Findings
IC-137
Pre-trained ResNet34 and ViT-B features on CIFAR-100 exhibit a block-diagonal class-correlation structure, with ViT-B showing higher intra-class correlation (0.35) than ResNet34 (0.25)
[eval]
IC-447
CLIP ViT-B/16 produces noisy saliency maps and contains only 42 concept detectors, indicating poor visual interpretability
[eval]