Cut-ViT: Task-Specific Model Pruning via Gram Anchoring Subspace Consistency
Read the original on arXiv Computer Vision →Cut‑ViT introduces a task‑specific pruning pipeline for visual foundation models that uses gram anchoring matrices and subspace decomposition to align feature representations between native and pruned DINOv3 models. The method incorporates basis‑agnostic and residual constraints to preserve robustness across spatial and channel dimensions, and employs spectral entropy adaptation to tailor the pruning objective to downstream tasks. Experiments demonstrate that Cut‑ViT achieves state‑of‑the‑art performance on six tasks across nine datasets while reducing pruning time to about one minute on a single A100 GPU, using only 20.9% of the time and 45.5% of the GPU memory compared to prior methods.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.