Lightweight Channel Attention for Efficient CNNs

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Kanaparthi, Prem Babu, Padamata, Tulasi Venkata Sri Varshini
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912800961462272
author Kanaparthi, Prem Babu
Padamata, Tulasi Venkata Sri Varshini
author_facet Kanaparthi, Prem Babu
Padamata, Tulasi Venkata Sri Varshini
contents Attention mechanisms have become integral to modern convolutional neural networks (CNNs), delivering notable performance improvements with minimal computational overhead. However, the efficiency accuracy trade off of different channel attention designs remains underexplored. This work presents an empirical study comparing Squeeze and Excitation (SE), Efficient Channel Attention (ECA), and a proposed Lite Channel Attention (LCA) module across ResNet 18 and MobileNetV2 architectures on CIFAR 10. LCA employs adaptive one dimensional convolutions with grouped operations to reduce parameter usage while preserving effective attention behavior. Experimental results show that LCA achieves competitive accuracy, reaching 94.68 percent on ResNet 18 and 93.10 percent on MobileNetV2, while matching ECA in parameter efficiency and maintaining favorable inference latency. Comprehensive benchmarks including FLOPs, parameter counts, and GPU latency measurements are provided, offering practical insights for deploying attention enhanced CNNs in resource constrained environments.
format Preprint
id arxiv_https___arxiv_org_abs_2601_01002
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Lightweight Channel Attention for Efficient CNNs
Kanaparthi, Prem Babu
Padamata, Tulasi Venkata Sri Varshini
Computer Vision and Pattern Recognition
Attention mechanisms have become integral to modern convolutional neural networks (CNNs), delivering notable performance improvements with minimal computational overhead. However, the efficiency accuracy trade off of different channel attention designs remains underexplored. This work presents an empirical study comparing Squeeze and Excitation (SE), Efficient Channel Attention (ECA), and a proposed Lite Channel Attention (LCA) module across ResNet 18 and MobileNetV2 architectures on CIFAR 10. LCA employs adaptive one dimensional convolutions with grouped operations to reduce parameter usage while preserving effective attention behavior. Experimental results show that LCA achieves competitive accuracy, reaching 94.68 percent on ResNet 18 and 93.10 percent on MobileNetV2, while matching ECA in parameter efficiency and maintaining favorable inference latency. Comprehensive benchmarks including FLOPs, parameter counts, and GPU latency measurements are provided, offering practical insights for deploying attention enhanced CNNs in resource constrained environments.
title Lightweight Channel Attention for Efficient CNNs
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.01002