MAAM is a multi-branch convolutional module with scalar-weighted fusion that reaches 87.0% on CIFAR-10, but it lacks comparisons with modern lightweight networks and its ablation results are internally inconsistent.
Shufflenet: An extremely efficient convolutional neural network for mobile devices
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
MAAM: A Lightweight Multi-Agent Aggregation Module for Efficient Image Classification Based on the MindSpore Framework
MAAM is a multi-branch convolutional module with scalar-weighted fusion that reaches 87.0% on CIFAR-10, but it lacks comparisons with modern lightweight networks and its ablation results are internally inconsistent.