Improving Fine-Tuning with Latent Cluster Correction
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 11 of its 35 references that are in the map. First posted on arXiv 21 Jan 2025.
Builds on
11 of 35 references.
References · 11
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2015Distilling the Knowledge in a Neural Networkcited by 10,076
- 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
- 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,841
- 2014FitNets: Hints for Thin Deep Netscited by 1,619
- 2018From Louvain to Leiden: guaranteeing well-connected communitiescited by 379
- 2020Model Rubik's Cube: Twisting Resolution, Depth and Width for TinyNetscited by 49
- 2018How deep is deep enough? -- Quantifying class separability in the hidden layers of deep neural networkscited by 28
- 2018Grassmannian Learning: Embedding Geometry Awareness in Shallow and Deep Learningcited by 19
- 2020Representing Deep Neural Networks Latent Space Geometries with Graphscited by 7
- 2019Introducing Graph Smoothness Loss for Training Deep Learning Architecturescited by 6
Built on by
Not cited yet.