Search papers, labs, and topics across Lattice.
This paper investigates the impact of hyperparameter optimization, specifically learning rate schedules, augmentation, optimizers, and initialization, on the accuracy and deployment feasibility of seven lightweight CNN and transformer architectures trained on a subset of ImageNet-1K. The study benchmarks inference latency and throughput on an NVIDIA L40s GPU, demonstrating the significant influence of hyperparameter tuning on convergence dynamics and model performance. The key finding is that hyperparameter optimization alone can improve top-1 accuracy by 1.5 to 3.5 percent, with select models achieving latency under 5ms and throughput over 9,800 FPS, suitable for edge deployment.
Hyperparameter tuning can boost the accuracy of lightweight image classification models by up to 3.5% and unlock real-time performance on edge devices.
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
