调参能提升轻量模型准确率1.5%-3.5%，加速至每秒9800帧。
Analysis of Hyperparameter Optimization Effects on Lightweight Deep Models for Real-Time Image Classification
- 系统测试7种轻量模型在不同超参数下的表现，控制变量分析影响。
- 调参后模型准确率提升1.5%~3.5%，部分模型延迟低于5毫秒。
- 结果可复现，适合边缘AI部署的模型选型与性能优化参考。
轻量级卷积与基于Transformer的网络在资源受限设备上的实时图像分类中日益流行。本研究评估了超参数优化对七种现代轻量架构（ConvNeXt-T、EfficientNetV2-S、MobileNetV3-L、MobileViT v2 (S/XS)、RepVGG-A2、TinyViT-21M）在90,000张图像子集（来自ImageNet-1K，类别均衡）上训练时的准确率与部署可行性的影响。在标准化训练设置下，本文研究学习率调度、数据增强、优化器和初始化对模型性能的影响。使用NVIDIA L40s GPU进行推理基准测试，批大小范围为1到512，捕捉实时条件下的延迟与吞吐量。结果表明，受控的超参数变化显著改变轻量级CNN与Transformer骨干网络的收敛动态，揭示稳定性区域与边缘人工智能部署可行性。调参可使顶1准确率相比基线提升1.5%至3.5%，部分模型（如RepVGG-A2、MobileNetV3-L）延迟低于5毫秒，吞吐量超过9,800帧/秒，非常适合边缘部署。本工作提供基于子集的可复现轻量超参数调优洞察，助力速度与准确率的平衡。代码与日志见：https://vineetkumarrakesh.github.io/lcnn-opt
原文摘要 · Abstract (English)
Lightweight convolutional and transformer-based networks are increasingly preferred for real-time image classification, especially on resource-constrained devices. This study evaluates the impact of hyperparameter optimization on the accuracy and deployment feasibility of seven modern lightweight architectures: ConvNeXt-T, EfficientNetV2-S, MobileNetV3-L, MobileViT v2 (S/XS), RepVGG-A2, and TinyViT-21M, trained on a class-balanced subset of 90,000 images from ImageNet-1K. Under standardized training settings, this paper investigates the influence of learning rate schedules, augmentation, optimizers, and initialization on model performance. Inference benchmarks are performed using an NVIDIA L40s GPU with batch sizes ranging from 1 to 512, capturing latency and throughput in real-time conditions. This work demonstrates that controlled hyperparameter variation significantly alters convergence dynamics in lightweight CNN and transformer backbones, providing insight into stability regions and deployment feasibility in edge artificial intelligence. Our results reveal that tuning alone leads to a top-1 accuracy improvement of 1.5 to 3.5 percent over baselines, and select models (e.g., RepVGG-A2, MobileNetV3-L) deliver latency under 5 milliseconds and over 9,800 frames per second, making them ideal for edge deployment. This work provides reproducible, subset-based insights into lightweight hyperparameter tuning and its role in balancing speed and accuracy. The code and logs may be seen at: https://vineetkumarrakesh.github.io/lcnn-opt
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。