#DINOv2

2 related articles

Jul 10, 2026·6 min

DINOv2 vs SigLIP: Why the Huge Gap in k-NN Classification? A Guide to Avoiding Vision Encoder Selection Pitfalls

Experiments show DINOv2 Giant scores just 41% on k-NN classification, while SigLIP2 reaches 92%. This article dives into the embedding-space differences between contrastive and self-supervised learning to guide vision encoder selection.

Jul 9, 2026·7 min

Block-Sparse Featurizers: Opening the Black Box of Vision Model Neural Geometry

Block-sparse featurizers remap dense vision model activations into block-sparse representations, making the internal feature spaces of ViT, CNN, and other models readable and interpretable. This article explores their core principles, links to mechanistic interpretability, and applications.