A Reproducible Benchmark of Lightweight CNNs: Accuracy, Efficiency, and the Impact of Pretrained Initialization

Abstract:Lightweight convolutional neural networks are often compared using results obtained with different training recipes, input settings, and pretrained checkpoints. Such differences make architecture rankings difficult to interpret. This study presents a reproducible benchmark of seven established CNNs across CIFAR-10, CIFAR-100, and Tiny ImageNet under one common fine-tuning protocol. The evaluation reports top-1 accuracy, macro F1, top-5 accuracy, parameter count, FP32 parameter storage, and multiply-accumulate operations. EfficientNetV2-S records the highest observed top-1 accuracy on all three datasets, reaching 97.57%, 86.98%, and 78.73%. EfficientNet-B0 remains within 0.85 percentage points of EfficientNetV2-S across the three datasets while requiring only about 21% of its parameters and 14% of its multiply-accumulate operations on Tiny ImageNet. It therefore offers a favorable general balance between predictive performance and computational demand. MobileNetV3-Small is a strong candidate for ultra-low-resource settings. It uses about 40% of the parameters and 15% of the multiply-accumulate operations of EfficientNet-B0 while retaining competitive accuracy. A matched comparison of ImageNet-pretrained and randomly initialized EfficientNet-B0 and MobileNetV3-Small models shows that the pretrained advantage is substantially larger on CIFAR-100 and Tiny ImageNet than on CIFAR-10 under the fixed protocol. The results provide a focused reference for selecting established lightweight CNNs when predictive quality, parameter storage, and theoretical computation must be considered together.

Submission history

From: Tasnim Shahriar [view email]
[v1] Tue, 6 May 2025 08:36:01 UTC (3,664 KB)
[v2] Tue, 9 Sep 2025 11:02:55 UTC (3,664 KB)
[v3] Tue, 30 Jun 2026 15:28:27 UTC (48 KB)
[v4] Wed, 1 Jul 2026 06:34:23 UTC (48 KB)

View PDF HTML (experimental)

Abstract:Lightweight convolutional neural networks are often compared using results obtained with different training recipes, input settings, and pretrained checkpoints. Such differences make architecture rankings difficult to interpret. This study presents a reproducible benchmark of seven established CNNs across CIFAR-10, CIFAR-100, and Tiny ImageNet under one common fine-tuning protocol. The evaluation reports top-1 accuracy, macro F1, top-5 accuracy, parameter count, FP32 parameter storage, and multiply-accumulate operations. EfficientNetV2-S records the highest observed top-1 accuracy on all three datasets, reaching 97.57%, 86.98%, and 78.73%. EfficientNet-B0 remains within 0.85 percentage points of EfficientNetV2-S across the three datasets while requiring only about 21% of its parameters and 14% of its multiply-accumulate operations on Tiny ImageNet. It therefore offers a favorable general balance between predictive performance and computational demand. MobileNetV3-Small is a strong candidate for ultra-low-resource settings. It uses about 40% of the parameters and 15% of the multiply-accumulate operations of EfficientNet-B0 while retaining competitive accuracy. A matched comparison of ImageNet-pretrained and randomly initialized EfficientNet-B0 and MobileNetV3-Small models shows that the pretrained advantage is substantially larger on CIFAR-100 and Tiny ImageNet than on CIFAR-10 under the fixed protocol. The results provide a focused reference for selecting established lightweight CNNs when predictive quality, parameter storage, and theoretical computation must be considered together.