FastBoost用动态注意力机制，在极小参数量下实现顶级图像分类性能。
FastBoost: Progressive Attention with Dynamic Scaling for Efficient Deep Learning
- 引入动态渐进注意力机制，自适应融合通道与空间信息。
- 在CIFAR-10上仅用0.37M参数达93.80%准确率，参数减少2.1倍。
- 适合边缘设备部署，兼顾高精度与低算力需求。
我们提出FastBoost，一种参数高效的神经网络架构，通过新颖的动态缩放渐进注意力（DSPA）机制，在CIFAR基准上达到顶尖性能。CIFAR-10：0.85M参数下准确率达95.57%，0.37M参数下为93.80%；CIFAR-100：0.92M参数下达81.37%，0.44M参数下为74.85%。DSPA的三大创新包括：(1) 自适应融合：学习通道-空间注意力并动态加权；(2) 阶段缩放：训练阶段感知的强度调制（0.5到1.0）；(3) 残差自适应：自优化跳接连接（γ从0.5到0.72）。结合增强型MBConv模块，FastBoost相比MobileNetV3参数减少2.1倍，且在CIFAR-10上准确率提升+3.2个百分点。架构具双注意力路径、实时权重调整、级联精炼层（梯度流提升12.7%），硬件友好设计仅需0.28G FLOPs。该动态注意力与高效卷积协同优化，实现前所未有的参数-精度平衡，可在资源受限的边缘设备上部署而无精度损失。
原文摘要 · Abstract (English)
We present FastBoost, a parameter-efficient neural architecture that achieves state-of-the-art performance on CIFAR benchmarks through a novel Dynamically Scaled Progressive Attention (DSPA) mechanism. Our design establishes new efficiency frontiers with: CIFAR-10: 95.57% accuracy (0.85M parameters) and 93.80% (0.37M parameters) CIFAR-100: 81.37% accuracy (0.92M parameters) and 74.85% (0.44M parameters) The breakthrough stems from three fundamental innovations in DSPA: (1) Adaptive Fusion: Learnt channel-spatial attention blending with dynamic weights. (2) Phase Scaling: Training-stage-aware intensity modulation (from 0.5 to 1.0). (3) Residual Adaptation: Self-optimized skip connections (gamma from 0.5 to 0.72). By integrating DSPA with enhanced MBConv blocks, FastBoost achieves a 2.1 times parameter reduction over MobileNetV3 while improving accuracy by +3.2 percentage points on CIFAR-10. The architecture features dual attention pathways with real-time weight adjustment, cascaded refinement layers (increasing gradient flow by 12.7%), and a hardware-friendly design (0.28G FLOPs). This co-optimization of dynamic attention and efficient convolution operations demonstrates unprecedented parameter-accuracy trade-offs, enabling deployment in resource-constrained edge devices without accuracy degradation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。