arXiv AI By Irene Trigueros-Lorca, Leonardo Concepci\'on, Christian Wagner, Isaac Triguero, Daniel Molina

Too much of a good thing -- when knowledge distillation promotes overfitting, and how to avoid it

Read the original on arXiv AI →

The paper investigates how knowledge distillation (KD) applied at intermediate layers of a neural network can affect overfitting and model performance. While traditional KD focuses on the final output, this study explores block‑wise KD across eleven datasets, finding that on standard datasets the last block suffices, but on fine‑grained, data‑scarce settings intermediate supervision significantly improves accuracy. The authors also analyze optimal supervision granularity using attention maps, Centered Kernel Alignment, and Grad‑CAM, and examine teacher‑student fine‑tuning strategies.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Hugging Face Trending Papers
Aug 11

Grid-Preserving Knowledge Distillation: Transferring Convolutional Inductive Bias to Vision Transformers under Data Scarcity

Vision Transformers underperform convolutional networks when training data is scarce, and distilling convolutional inductive biases from a CNN teacher is an effective remedy that leaves the deployed model unchanged. General-purpose feature distillation, however, transfers little in this setting.

arXiv Machine Learning
Jun 4

Breaking the Scale Barrier: One-Shot Knowledge Transfer via Frequency Transform

arXiv:2603. 07523v3 Announce Type: replace Abstract: Transferring knowledge by fine-tuning large-scale pre-trained networks has become a standard paradigm for downstream tasks, yet the knowledge of a pre-trained model is tightly coupled with monolithic architecture, which restricts flexible reuse across models of varying scales.

By Jianlu Shen, Fu Feng, Yucheng Xie, Jiaqi Lv, Xin Geng