# Scale Decoupled Distillation

arXiv: https://arxiv.org/abs/2403.13512 · HTML: https://mlsanity.com/paper/2403.13512/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in General knowledge distillation methods, one of 12 directions in Knowledge distillation.
- Builds on 19 of its 25 references that are in the map.
- First posted on arXiv 20 Mar 2024.

## Placed in

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

## Builds on (most cited first, 19 of 19)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020)
- [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)
- [Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition](https://mlsanity.com/paper/1406.4729/) (2014)
- [Similarity-Preserving Knowledge Distillation](https://mlsanity.com/paper/1907.09682/) (2019)
- [Decoupled Knowledge Distillation](https://mlsanity.com/paper/2203.08679/) (2022)
- [Distilling Knowledge via Knowledge Review](https://mlsanity.com/paper/2104.09044/) (2021)
- [Knowledge Distillation by On-the-Fly Native Ensemble](https://mlsanity.com/paper/1806.04606/) (2018)
- [Cross-Layer Distillation with Semantic Calibration](https://mlsanity.com/paper/2012.03236/) (2020)
- [Knowledge Distillation Meets Self-Supervision](https://mlsanity.com/paper/2006.07114/) (2020)
- [Knowledge Distillation with the Reused Teacher Classifier](https://mlsanity.com/paper/2203.14001/) (2022)
- [Rethinking Soft Labels for Knowledge Distillation: A Bias-Variance Tradeoff Perspective](https://mlsanity.com/paper/2102.00650/) (2021)
- [From Knowledge Distillation to Self-Knowledge Distillation: A Unified Approach with Normalized Loss and Customized Soft Labels](https://mlsanity.com/paper/2303.13005/) (2023)
- [Knowledge Transfer via Dense Cross-Layer Mutual-Distillation](https://mlsanity.com/paper/2008.07816/) (2020)
- [KDExplainer: A Task-oriented Attention Model for Explaining Knowledge Distillation](https://mlsanity.com/paper/2105.04181/) (2021)

## Built on by (most cited first, 5 of 5)

- [VRM: Knowledge Distillation via Virtual Relation Matching](https://mlsanity.com/paper/2502.20760/) (2025)
- [Cross-Architecture Distillation Made Simple with Redundancy Suppression](https://mlsanity.com/paper/2507.21844/) (2025)
- [LoCa: Logit Calibration for Knowledge Distillation](https://mlsanity.com/paper/2409.04778/) (2024)
- [SAMKD: Spatial-aware Adaptive Masking Knowledge Distillation for Object Detection](https://mlsanity.com/paper/2501.07101/) (2025)
- [Contrastive Representation Distillation via Multi-Scale Feature Decoupling](https://mlsanity.com/paper/2502.05835/) (2025)

## Abstract (arXiv)

Logit knowledge distillation attracts increasing attention due to its practicality in recent studies. However, it often suffers inferior performance compared to the feature knowledge distillation. In this paper, we argue that existing logit-based methods may be sub-optimal since they only leverage the global logit output that couples multiple semantic knowledge. This may transfer ambiguous knowledge to the student and mislead its learning. To this end, we propose a simple but effective method, i.e., Scale Decoupled Distillation (SDD), for logit knowledge distillation. SDD decouples the global logit output into multiple local logit outputs and establishes distillation pipelines for them. This helps the student to mine and inherit fine-grained and unambiguous logit knowledge. Moreover, the decoupled knowledge can be further divided into consistent and complementary logit knowledge that transfers the semantic information and sample ambiguity, respectively. By increasing the weight of complementary parts, SDD can guide the student to focus more on ambiguous samples, improving its discrimination ability. Extensive experiments on several benchmark datasets demonstrate the effectiveness of SDD for wide teacher-student pairs, especially in the fine-grained classification task. Code is available at: https://github.com/shicaiwei123/SDD-CVPR2024