Caltech-256

Findings

• IC-137Pre-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-447CLIP ViT-B/16 produces noisy saliency maps and contains only 42 concept detectors, indicating poor visual interpretability [eval]