调整激活函数可提升模型识别准确率，尤其在CIFAR-10上效果显著。
Evaluating Model Performance with Hard-Swish Activation Function Adjustments
- 用Hard-Swish替代ReLU改进模型激活机制。
- CIFAR-10上准确率提升2.06%，ATLAS上提升0.30%。
- 适合关注模型微调与性能优化的研究者。
在模式识别领域，高准确率至关重要。训练模型识别复杂图像时，精细调参是关键。本文评估了使用ReLU、Swish和Hard-Swish三种激活函数的模型在多个图像数据集上的表现。结果表明，在CIFAR-10数据集上，采用Hard-Swish的模型准确率提升了2.06%；在ATLAS数据集上提升了0.30%。对预训练模型的激活函数进行调整，能有效提升整体准确率。
原文摘要 · Abstract (English)
In the field of pattern recognition, achieving high accuracy is essential. While training a model to recognize different complex images, it is vital to fine-tune the model to achieve the highest accuracy possible. One strategy for fine-tuning a model involves changing its activation function. Most pre-trained models use ReLU as their default activation function, but switching to a different activation function like Hard-Swish could be beneficial. This study evaluates the performance of models using ReLU, Swish and Hard-Swish activation functions across diverse image datasets. Our results show a 2.06% increase in accuracy for models on the CIFAR-10 dataset and a 0.30% increase in accuracy for models on the ATLAS dataset. Modifying the activation functions in architecture of pre-trained models lead to improved overall accuracy.
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。