Zero-ablation overstates register content dependence in DINO ViTs because mean, noise, and cross-image shuffle replacements preserve performance while zeroing does not.
DINOv3 models are loaded via torch.hub with locally cached weights ( dinov3 vits16 and dinov3 vitb16)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Zero-Ablation Overstates Register Content Dependence in DINO Vision Transformers
Zero-ablation overstates register content dependence in DINO ViTs because mean, noise, and cross-image shuffle replacements preserve performance while zeroing does not.