2026-10-10T17:55:16Z https://api.figshare.com/v2/oai

oai:figshare.com:article/33814197 2026-09-15T17:56:32Z category_146 category_7 category_21 category_873 category_734 category_931 portal_5 item_type_3 month_year_09_2026

<p>Performance comparison of different network architectures and attention modules – CIFAR-10 dataset.</p> Guangjun Liu (3932987) Xiaoping Xu (325842) Bingkun Zhou (12267614) Feng Wang (44414) Yike Li (1529680) Space Science Medicine Biotechnology Chemical Sciences not elsewhere classified Biological Sciences not elsewhere classified Information Systems not elsewhere classified small flops overhead representative attention modules play cnn architectures negligible computational overhead fully connected layers emphasizing informative features dimensional attention weights deterministic weighted fusion costs may limit compute adaptive three 81 percentage points 68 percentage points efficient attention module 100 using resnet tanh activation results show pooling branches pointwise average paper proposes original backbones model compactness mobilenetv2 backbones channel statistics best accuracy 9 settings <p>Performance comparison of different network architectures and attention modules – CIFAR-10 dataset.</p> 2026-09-15T17:56:20Z Dataset Dataset 10.1371/journal.pone.0357958.t002 https://figshare.com/articles/dataset/_p_Performance_comparison_of_different_network_architectures_and_attention_modules_CIFAR-10_dataset_p_/33814197 CC BY 4.0