无需训练，通过重播视觉骨干提升模型在分布偏移下的鲁棒性。
GramLoop: Training-Free Gram-Gated Replay for Robust Dense Prediction
- 重播短窗口Transformer层并用余弦Gram一致性控制每轮重播
- 在五个分布偏移基准上均优于基线，COCO-O mAP提升0.252
- 适用于部署后优化冻结模型，适合工业级落地场景
我们旨在通过在视觉骨干中引入推理阶段计算，不修改模型权重、任务适配器或预测头，提升冻结的DINOv3密集预测模型在分布偏移下的性能。难点在于重复的Transformer块计算需优化密集特征，同时不破坏DINOv3用于保持空间结构的成对图块关系。我们提出GramLoop，一种无需训练的框架，通过最终层余弦Gram一致性控制短Transformer窗口的重播。每个提案经由冻结的后缀传播，与标准DINOv3轨迹对比，并在重播窗口终点通过逐图块门控决定是否接受。在多种噪声、扰动和自然分布偏移下，GramLoop在所有五个偏移基准上均优于配对的DINOv3基线。在COCO-O上，mAP提升0.252，有效鲁棒性提升0.250，同时保持清洁ADE20K性能。代码将开源。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。