通过优化隐空间聚类提升微调性能，让模型更准
Improving Fine-Tuning with Latent Cluster Correction
- 用Louvain算法识别神经网络隐空间的语义聚类
- 设计聚类损失函数，使训练中聚类更清晰
- 在CIFAR-100上验证有效，适合图像分类微调
神经网络训练过程中隐空间中显著的语义聚类与最终分类准确率高度相关。本文提出一种新型微调方法，通过优化这些隐空间聚类的形成来提升性能，采用Louvain社区检测算法并设计专门的聚类损失函数。初步实验表明该方法在经典神经网络架构上对CIFAR-100数据集的微调中具有可行性。
原文摘要 · Abstract (English)
The existence of salient semantic clusters in the latent spaces of a neural network during training strongly correlates its final accuracy on classification tasks. This paper proposes a novel fine-tuning method that boosts performance by optimising the formation of these latent clusters, using the Louvain community detection algorithm and a specifically designed clustering loss function. We present preliminary results that demonstrate the viability of this process on classical neural network architectures during fine-tuning on the CIFAR-100 dataset.
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。