arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2605.08136cs.CVcs.AIcs.RO
收藏

在RT-DETR中评估ResNet主干:环境条件下深度和正则化的影响

Benchmarking ResNet Backbones in RT-DETR: Impact of Depth and Regularization under environmental conditions

Robotics and Artificial Intelligence Laboratory, Technological University of Uruguay(机器人与人工智能实验室,乌拉圭技术大学);Artificial Intelligence Laboratory, Technological University of Uruguay(人工智能实验室,乌拉圭技术大学)

Pamela Barboza, Víctor Castelli, Belén Pereira, Ricardo Grando, Bruna de Vargas, Augusto Calfani

AI总结:

本文评估RT-DETR在环境和超参数变化下的圆物体检测性能,比较了四种ResNet主干在不同丢弃率下的置信度和准确率,发现ResNet50在光照变化中表现最佳,ResNet34在背景变化中表现最佳。

摘要:

视觉感知在竞争性机器人中起着核心作用,其中环境变化可能直接影响实时检测性能。现有的基于变换器的检测器文献缺乏关于主干规模和环境设置对模型性能影响的信息。本文提出了对RT-DETR的比较评估,以检测环境和超参数变化相关的圆物体。通过比较四种ResNet主干(ResNet18、ResNet34、ResNet50和ResNet101)的丢弃率,分析了它们对置信度和准确率的影响。所有模型均在相同配置下训练,并在光照和背景对比变化下进行评估。环境条件主要影响预测置信度,而推理延迟基本不受影响,分类准确率保持一致较高,大多数情况下接近或超过1.00。观察到两种不同的行为。在光照变化下,ResNet50实现了最佳的权衡,结合接近完美的准确率、置信值高达约0.869和延迟约0.058-0.059 ms。在背景变化下,ResNet34提供了最平衡的性能,达到接近完美的准确率和更高的置信值,高达约0.887。这些结果表明,最佳架构取决于环境变化类型,中间深度模型在性能和效率之间提供了最佳平衡。

英文摘要:

Visual perception plays a central role in competitive robotics, where environmental variations can directly affect real-time detection performance. The related literature on transformer-based detectors lack information regarding the impact of backbone scale and environmental settings on model performance. This work presents a comparative evaluation of RT-DETR for detecting round objects under environmental and hyperparameter variations relevant to competitive robotics. Four ResNet backbones (ResNet18, ResNet34, ResNet50, and ResNet101) were compared using dropout rates, analyzing their effect on confidence and accuracy. All models were trained under the same configuration and evaluated under changes in lighting and background contrast. Environmental conditions primarily impact prediction confidence, while inference latency remains largely unaffected and classification accuracy stays consistently high, approaching or above 1.00 in most cases. Two distinct behaviors were observed. Under illumination variation, ResNet50 achieves the best trade-off, combining near-perfect accuracy, confidence values up to approximately 0.869 and latency around 0.058-0.059 ms. Under background variation, ResNet34 provides the most balanced performance, reaching near-perfect accuracy and higher confidence values up to approximately 0.887. These results indicate that the optimal architecture depends on the type of environmental variation, with intermediate-depth models offering the best balance between performance and efficiency.

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。

↑