arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2511.09554cs.CV
收藏

RF-DETR:实时检测Transformer的神经架构搜索

RF-DETR: Neural Architecture Search for Real-Time Detection Transformers

Roboflow;Carnegie Mellon University(卡内基梅隆大学)

Isaac Robinson, Peter Robicheaux, Matvei Popov, Deva Ramanan, Neehar Peri

AI总结:

RF-DETR通过轻量级检测Transformer和神经架构搜索,在实时检测中实现更高的精度和速度,超越现有方法。

摘要:

开放词汇检测器在COCO数据集上实现了出色的性能,但往往无法泛化到现实世界的数据集,尤其是那些包含分布外类别的数据集,这些类别在预训练时并不常见。与其简单地对重模型进行微调以适应新领域,我们提出了RF-DETR,这是一种轻量级的专用检测Transformer,通过具有权重共享的神经架构搜索(NAS)发现任何目标数据集的精度-延迟帕累托曲线。我们的方法在目标数据集上微调预训练的基网络,并评估成千上万种具有不同精度-延迟权衡的网络配置,而无需重新训练。此外,我们重新审视NAS的“可调旋钮”,以提高DETRs在多样目标领域中的可迁移性。值得注意的是,RF-DETR在COCO和Roboflow100-VL上显著优于先前最先进的实时方法。RF-DETR(nano)在COCO上达到48.0 AP,比D-FINE(nano)在相似延迟下高出5.3 AP,而RF-DETR(2x-large)在Roboflow100-VL上超越GroundingDINO(tiny)1.2 AP,运行速度比GroundingDINO(tiny)快20倍。据我们所知,RF-DETR(2x-large)是首个在COCO上超越60 AP的实时检测器。我们的代码可在https://github.com/roboflow/rf-detr上获得。

英文摘要:

Open-vocabulary detectors achieve impressive performance on COCO, but often fail to generalize to real-world datasets with out-of-distribution classes not typically found in their pre-training. Rather than simply fine-tuning a heavy-weight vision-language model (VLM) for new domains, we introduce RF-DETR, a light-weight specialist detection transformer that discovers accuracy-latency Pareto curves for any target dataset with weight-sharing neural architecture search (NAS). Our approach fine-tunes a pre-trained base network on a target dataset and evaluates thousands of network configurations with different accuracy-latency tradeoffs without re-training. Further, we revisit the "tunable knobs" for NAS to improve the transferability of DETRs to diverse target domains. Notably, RF-DETR significantly improves over prior state-of-the-art real-time methods on COCO and Roboflow100-VL. RF-DETR (nano) achieves 48.0 AP on COCO, beating D-FINE (nano) by 5.3 AP at similar latency, and RF-DETR (2x-large) outperforms GroundingDINO (tiny) by 1.2 AP on Roboflow100-VL while running 20x as fast. To the best of our knowledge, RF-DETR (2x-large) is the first real-time detector to surpass 60 AP on COCO. Our code is available at https://github.com/roboflow/rf-detr

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑