# Logit Standardization in Knowledge Distillation

arXiv: https://arxiv.org/abs/2403.01427 · HTML: https://mlsanity.com/paper/2403.01427/

## Key facts

- Cited by 102 papers in the map (data through 14 Oct 2026).
- Placed in General knowledge distillation methods, one of 12 directions in Knowledge distillation.
- Builds on 44 of its 57 references that are in the map.
- First posted on arXiv 3 Mar 2024.

## Placed in

- Knowledge distillation / [General knowledge distillation methods](https://mlsanity.com/distill/general-knowledge-distillation-methods/)

## Builds on (most cited first, 30 of 44)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices](https://mlsanity.com/paper/1707.01083/) (2017)
- [Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer](https://mlsanity.com/paper/1612.03928/) (2016)
- [Relational Knowledge Distillation](https://mlsanity.com/paper/1904.05068/) (2019)
- [Contrastive Representation Distillation](https://mlsanity.com/paper/1910.10699/) (2019)
- [Deep Mutual Learning](https://mlsanity.com/paper/1706.00384/) (2017)
- [Improved Knowledge Distillation via Teacher Assistant](https://mlsanity.com/paper/1902.03393/) (2019)
- [Similarity-Preserving Knowledge Distillation](https://mlsanity.com/paper/1907.09682/) (2019)
- [MaxViT: Multi-Axis Vision Transformer](https://mlsanity.com/paper/2204.01697/) (2022)
- [Decoupled Knowledge Distillation](https://mlsanity.com/paper/2203.08679/) (2022)
- [On the Efficacy of Knowledge Distillation](https://mlsanity.com/paper/1910.01348/) (2019)
- [A Comprehensive Overhaul of Feature Distillation](https://mlsanity.com/paper/1904.01866/) (2019)
- [Variational Information Distillation for Knowledge Transfer](https://mlsanity.com/paper/1904.05835/) (2019)
- [Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlooks](https://mlsanity.com/paper/2004.05937/) (2020)
- [Distilling Knowledge via Knowledge Review](https://mlsanity.com/paper/2104.09044/) (2021)
- [Correlation Congruence for Knowledge Distillation](https://mlsanity.com/paper/1904.01802/) (2019)
- [Structured Knowledge Distillation for Dense Prediction](https://mlsanity.com/paper/1903.04197/) (2019)
- [TinyViT: Fast Pretraining Distillation for Small Vision Transformers](https://mlsanity.com/paper/2207.10666/) (2022)
- [Knowledge Distillation from A Stronger Teacher](https://mlsanity.com/paper/2205.10536/) (2022)
- [Knowledge Distillation with the Reused Teacher Classifier](https://mlsanity.com/paper/2203.14001/) (2022)

## Built on by (most cited first, 30 of 102)

- [TrojVLM: Backdoor Attack Against Vision Language Models](https://mlsanity.com/paper/2409.19232/) (2024)
- [LLAVADI: What Matters For Multimodal Large Language Models Distillation](https://mlsanity.com/paper/2407.19409/) (2024)
- [ABKD: Pursuing a Proper Allocation of the Probability Mass in Knowledge Distillation via α-β-Divergence](https://mlsanity.com/paper/2505.04560/) (2025)
- [LLM-Oriented Token-Adaptive Knowledge Distillation](https://mlsanity.com/paper/2510.11615/) (2025)
- [Knowledge Distillation with Refined Logits](https://mlsanity.com/paper/2408.07703/) (2024)
- [Semi-Supervised State-Space Model with Dynamic Stacking Filter for Real-World Video Deraining](https://mlsanity.com/paper/2505.16811/) (2025)
- [CKD: Contrastive Knowledge Distillation from A Sample-wise Perspective](https://mlsanity.com/paper/2404.14109/) (2024)
- [DisCoM-KD: Cross-Modal Knowledge Distillation via Disentanglement Representation and Adversarial Learning](https://mlsanity.com/paper/2408.07080/) (2024)
- [VRM: Knowledge Distillation via Virtual Relation Matching](https://mlsanity.com/paper/2502.20760/) (2025)
- [Aligning in a Compact Space: Contrastive Knowledge Distillation between Heterogeneous Architectures](https://mlsanity.com/paper/2405.18524/) (2024)
- [DiffKillR: Killing and Recreating Diffeomorphisms for Cell Annotation in Dense Microscopy Images](https://mlsanity.com/paper/2410.03058/) (2024)
- [Distillation of Large Language Models via Concrete Score Matching](https://mlsanity.com/paper/2509.25837/) (2025)
- [Diversity-Aware Reverse Kullback-Leibler Divergence for Large Language Model Distillation](https://mlsanity.com/paper/2604.00223/) (2026)
- [Exploring Dark Knowledge under Various Teacher Capacities and Addressing Capacity Mismatch](https://mlsanity.com/paper/2405.13078/) (2024)
- [Fuse Before Transfer: Knowledge Fusion for Heterogeneous Distillation](https://mlsanity.com/paper/2410.12342/) (2024)
- [Sample-level Adaptive Knowledge Distillation for Action Recognition](https://mlsanity.com/paper/2504.00606/) (2025)
- [Scalable Strategies for Continual Learning with Replay](https://mlsanity.com/paper/2505.12512/) (2025)
- [DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer](https://mlsanity.com/paper/2505.15133/) (2025)
- [Local Dense Logit Relations for Enhanced Knowledge Distillation](https://mlsanity.com/paper/2507.15911/) (2025)
- [Cross-Architecture Distillation Made Simple with Redundancy Suppression](https://mlsanity.com/paper/2507.21844/) (2025)
- [GeRe: Towards Efficient Anti-Forgetting in Continual Learning of LLM via General Samples Replay](https://mlsanity.com/paper/2508.04676/) (2025)
- [Learning Task-Agnostic Representations through Multi-Teacher Distillation](https://mlsanity.com/paper/2510.18680/) (2025)
- [Enhancing Logits Distillation with Plug&Play Kendall's τ Ranking Loss](https://mlsanity.com/paper/2409.17823/) (2024)
- [LoCa: Logit Calibration for Knowledge Distillation](https://mlsanity.com/paper/2409.04778/) (2024)
- [Learn from Balance: Rectifying Knowledge Transfer for Long-Tailed Scenarios](https://mlsanity.com/paper/2409.07694/) (2024)
- [Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks](https://mlsanity.com/paper/2412.19354/) (2024)
- [Adaptive Conformal Guidance for Learning under Uncertainty](https://mlsanity.com/paper/2502.16736/) (2025)
- [Adaptive Temperature Based on Logits Correlation in Knowledge Distillation](https://mlsanity.com/paper/2503.09030/) (2025)
- [Dual-Forward Path Teacher Knowledge Distillation: Bridging the Capacity Gap Between Teacher and Student](https://mlsanity.com/paper/2506.18244/) (2025)
- [Holmes: Towards Effective and Harmless Model Ownership Verification to Personalized Large Vision Models via Decoupling Common Features](https://mlsanity.com/paper/2507.00724/) (2025)

## Abstract (arXiv)

Knowledge distillation involves transferring soft labels from a teacher to a student using a shared temperature-based softmax function. However, the assumption of a shared temperature between teacher and student implies a mandatory exact match between their logits in terms of logit range and variance. This side-effect limits the performance of student, considering the capacity discrepancy between them and the finding that the innate logit relations of teacher are sufficient for student to learn. To address this issue, we propose setting the temperature as the weighted standard deviation of logit and performing a plug-and-play Z-score pre-process of logit standardization before applying softmax and Kullback-Leibler divergence. Our pre-process enables student to focus on essential logit relations from teacher rather than requiring a magnitude match, and can improve the performance of existing logit-based distillation methods. We also show a typical case where the conventional setting of sharing temperature between teacher and student cannot reliably yield the authentic distillation evaluation; nonetheless, this challenge is successfully alleviated by our Z-score. We extensively evaluate our method for various student and teacher models on CIFAR-100 and ImageNet, showing its significant superiority. The vanilla knowledge distillation powered by our pre-process can achieve favorable performance against state-of-the-art methods, and other distillation variants can obtain considerable gain with the assistance of our pre-process.