PaperScope
LIVE · 2026-09-03 05:40 UTC

GramLoop: Training-Free Gram-Gated Replay for Robust Dense Prediction

Yang Chen, Canyu Shen, Xinzhe Rao, Yuanyi Yan, Yunlu Chen, Meng Tang, Teng Long, Vincent Tao Hu

Latestcs.CLcs.LGcs.AIcs.CV
arXiv ID
2608.29113 v1
Category
Submitted
2026-08-29

Abstract

We aim to improve frozen DINOv3 dense-prediction models under distribution shift by adding inference computation inside the visual backbone, without changing model weights, task adapters, or prediction heads. The challenge is that repeated transformer-block computation must refine dense features without disrupting the pairwise patch relations that DINOv3 uses to preserve spatial structure. We introduce GramLoop, a training-free framework that replays a short transformer window and controls each replay through final-layer cosine-Gram consistency. Each proposal is propagated through the frozen suffix, measured against the standard DINOv3 trajectory, and accepted through a patchwise gate at the replay-window endpoint. Across object detection and semantic segmentation under corruptions, perturbations, and natural shifts, GramLoop improves all five shifted benchmarks over the paired DINOv3 baseline. On COCO-O, it improves mAP by +0.252 and Effective Robustness by +0.250, while preserving clean ADE20K performance. Code will be released.

arXiv abs page · PDF · same-day batch