LiDeRe：面向快速且数据高效密集预测的轻量读出模块
LiDeRe: A Lightweight Readout for Fast and Data-Efficient Dense Prediction
在冻结的大型视觉骨干（如 DINOv3）之上，用一个由插值与注意力构成的轻量密集读出模块替代主流 PEFT，为小数据下的分割、检测、姿态估计等密集预测任务提供更省参数、更快训练的微调范式。
原文依据 a well-designed and lightweight dense readout on top of a frozen large backbone can surpass state-of-the-art PEFT methods
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论参数高效微调（PEFT）方法近期因能降低过拟合、简化部署并支持快速训练，而在小数据集上应用深度神经网络时受到青睐。我们证明，在密集图像预测任务中，于冻结的大型骨干网络之上设计良好的轻量密集读出模块，可在效率与精度两方面超越最优的 PEFT 方法。我们的参数高效读出模块结合插值与注意力以实现细粒度密集预测，可与 DINOv3 等多种预训练视觉骨干网络无缝集成，并能与低秩适配（LoRA）结合使用。我们在语义分割、目标检测、姿态估计和语义轮廓预测上取得有竞争力或更优的性能，为现有 PEFT 技术提供了一种高效替代方案。
英文原文摘要 869 字符
Parameter-efficient fine-tuning (PEFT) methods have recently gained popularity for applying deep neural networks on small datasets as they reduce overfitting, simplify deployment, and enable fast training. We demonstrate that for dense image prediction tasks, a well-designed and lightweight dense readout on top of a frozen large backbone can surpass state-of-the-art PEFT methods in both efficiency and accuracy. Our parameter-efficient readout module combines interpolation and attention for fine-grained dense prediction. It integrates seamlessly with a wide range of pretrained vision backbones such as DINOv3 and can be combined with low-rank adaptation (LoRA). We achieve competitive or superior performance in semantic segmentation, object detection, pose estimation and semantic contour prediction, offering an efficient alternative to current PEFT techniques.