# MAAM: A Lightweight Multi-Agent Aggregation Module for Efficient Image Classification Based on the MindSpore Framework

arXiv: https://arxiv.org/abs/2504.13574 · HTML: https://mlsanity.com/paper/2504.13574/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 18 references that are in the map.
- First posted on arXiv 18 Apr 2025.

## Builds on (most cited first, 5 of 5)

- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices](https://mlsanity.com/paper/1707.01083/) (2017)
- [Dynamic Convolution: Attention over Convolution Kernels](https://mlsanity.com/paper/1912.03458/) (2019)
- [Exploring Self-attention for Image Recognition](https://mlsanity.com/paper/2004.13621/) (2020)
- [Dynamic Region-Aware Convolution](https://mlsanity.com/paper/2003.12243/) (2020)

## Abstract (arXiv)

The demand for lightweight models in image classification tasks under resource-constrained environments necessitates a balance between computational efficiency and robust feature representation. Traditional attention mechanisms, despite their strong feature modeling capability, often struggle with high computational complexity and structural rigidity, limiting their applicability in scenarios with limited computational resources (e.g., edge devices or real-time systems). To address this, we propose the Multi-Agent Aggregation Module (MAAM), a lightweight attention architecture integrated with the MindSpore framework. MAAM employs three parallel agent branches with independently parameterized operations to extract heterogeneous features, adaptively fused via learnable scalar weights, and refined through a convolutional compression layer. Leveraging MindSpore's dynamic computational graph and operator fusion, MAAM achieves 87.0% accuracy on the CIFAR-10 dataset, significantly outperforming conventional CNN (58.3%) and MLP (49.6%) models, while improving training efficiency by 30%. Ablation studies confirm the critical role of agent attention (accuracy drops to 32.0% if removed) and compression modules (25.5% if omitted), validating their necessity for maintaining discriminative feature learning. The framework's hardware acceleration capabilities and minimal memory footprint further demonstrate its practicality, offering a deployable solution for image classification in resource-constrained scenarios without compromising accuracy.