# Finet: Using Fine-grained Batch Normalization to Train Light-weight Neural Networks Source: [Finet: Using Fine-grained Batch Normalization to Train Light-weight Neural Networks]() Collection index: [llms.txt]() Data updated: 2025-10-25T22:16:13.371Z Authors: Chunjie Luo, Jianfeng Zhan, Lei Wang, Wanling Gao Published: 2020-05-14T09:16:13.000Z ## Abstract To build light-weight network, we propose a new normalization, Fine-grained Batch Normalization (FBN). Different from Batch Normalization (BN), which normalizes the final summation of the weighted inputs, FBN normalizes the intermediate state of the summation. We propose a novel light-weight network based on FBN, called Finet. At training time, the convolutional layer with FBN can be seen as an inverted bottleneck mechanism. FBN can be fused into convolution at inference time. After fusion, Finet uses the standard convolution with equal channel width, thus makes the inference more efficient. On ImageNet classification dataset, Finet achieves the state-of-art performance (65.706% accuracy with 43M FLOPs, and 73.786% accuracy with 303M FLOPs), Moreover, experiments show that Finet is more efficient than other state-of-art light-weight networks. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()