# Curriculum Temperature for Knowledge Distillation

arXiv: https://arxiv.org/abs/2211.16231 · HTML: https://mlsanity.com/paper/2211.16231/

## Key facts

- Cited by 112 papers in the map (data through 14 Oct 2026).
- Placed in General knowledge distillation methods, one of 12 directions in Knowledge distillation.
- Builds on 47 of its 60 references that are in the map.
- First posted on arXiv 29 Nov 2022.

## Placed in

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

## Builds on (most cited first, 30 of 47)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [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)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [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)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [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)
- [ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design](https://mlsanity.com/paper/1807.11164/) (2018)
- [Relational Knowledge Distillation](https://mlsanity.com/paper/1904.05068/) (2019)
- [Contrastive Representation Distillation](https://mlsanity.com/paper/1910.10699/) (2019)
- [MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels](https://mlsanity.com/paper/1712.05055/) (2017)
- [Similarity-Preserving Knowledge Distillation](https://mlsanity.com/paper/1907.09682/) (2019)
- [Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection](https://mlsanity.com/paper/2006.04388/) (2020)
- [Decoupled Knowledge Distillation](https://mlsanity.com/paper/2203.08679/) (2022)
- [Variational Information Distillation for Knowledge Transfer](https://mlsanity.com/paper/1904.05835/) (2019)
- [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)
- [Learning Deep Representations with Probabilistic Knowledge Transfer](https://mlsanity.com/paper/1803.10837/) (2018)
- [Competence-based Curriculum Learning for Neural Machine Translation](https://mlsanity.com/paper/1903.09848/) (2019)
- [Reverse Curriculum Generation for Reinforcement Learning](https://mlsanity.com/paper/1707.05300/) (2017)
- [Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed Classification](https://mlsanity.com/paper/2001.01536/) (2020)

## Built on by (most cited first, 30 of 112)

- [Logit Standardization in Knowledge Distillation](https://mlsanity.com/paper/2403.01427/) (2024)
- [CLIP-KD: An Empirical Study of CLIP Model Distillation](https://mlsanity.com/paper/2307.12732/) (2023)
- [PromptKD: Unsupervised Prompt Distillation for Vision-Language Models](https://mlsanity.com/paper/2403.02781/) (2024)
- [Frequency-Aligned Knowledge Distillation for Lightweight Spatiotemporal Forecasting](https://mlsanity.com/paper/2507.02939/) (2025)
- [CrossKD: Cross-Head Knowledge Distillation for Object Detection](https://mlsanity.com/paper/2306.11369/) (2023)
- [Knowledge Distillation Based on Transformed Teacher Matching](https://mlsanity.com/paper/2402.11148/) (2024)
- [RzenEmbed: Towards Comprehensive Multimodal Retrieval](https://mlsanity.com/paper/2510.27350/) (2025)
- [Text2LiDAR: Text-guided LiDAR Point Cloud Generation via Equirectangular Transformer](https://mlsanity.com/paper/2407.19628/) (2024)
- [Bayes Conditional Distribution Estimation for Knowledge Distillation Based on Conditional Mutual Information](https://mlsanity.com/paper/2401.08732/) (2024)
- [TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language Models](https://mlsanity.com/paper/2501.16937/) (2025)
- [Is Synthetic Data From Diffusion Models Ready for Knowledge Distillation?](https://mlsanity.com/paper/2305.12954/) (2023)
- [Advancing Textual Prompt Learning with Anchored Attributes](https://mlsanity.com/paper/2412.09442/) (2024)
- [Cascade Prompt Learning for Vision-Language Model Adaptation](https://mlsanity.com/paper/2409.17805/) (2024)
- [Wasserstein Distance Rivals Kullback-Leibler Divergence for Knowledge Distillation](https://mlsanity.com/paper/2412.08139/) (2024)
- [SeaFormer++: Squeeze-enhanced Axial Transformer for Mobile Visual Recognition](https://mlsanity.com/paper/2301.13156/) (2023)
- [Quantization Variation: A New Perspective on Training Transformers with Low-Bit Precision](https://mlsanity.com/paper/2307.00331/) (2023)
- [Distribution-Aligned Sequence Distillation for Superior Long-CoT Reasoning](https://mlsanity.com/paper/2601.09088/) (2026)
- [A Review of Pseudo-Labeling for Computer Vision](https://mlsanity.com/paper/2408.07221/) (2024)
- [Adaptive Teacher Exposure for Self-Distillation in LLM Reasoning](https://mlsanity.com/paper/2605.11458/) (2026)
- [Mitigating Accuracy-Robustness Trade-off via Balanced Multi-Teacher Adversarial Distillation](https://mlsanity.com/paper/2306.16170/) (2023)
- [LLM-Oriented Token-Adaptive Knowledge Distillation](https://mlsanity.com/paper/2510.11615/) (2025)
- [Curricular Object Manipulation in LiDAR-based Object Detection](https://mlsanity.com/paper/2304.04248/) (2023)
- [AMD: Automatic Multi-step Distillation of Large-scale Vision Models](https://mlsanity.com/paper/2407.04208/) (2024)
- [GripRank: Bridging the Gap between Retrieval and Generation via the Generative Knowledge Improved Passage Ranking](https://mlsanity.com/paper/2305.18144/) (2023)
- [To Cool or not to Cool? Temperature Network Meets Large Foundation Models via DRO](https://mlsanity.com/paper/2404.04575/) (2024)
- [Rapid Salient Object Detection with Difference Convolutional Neural Networks](https://mlsanity.com/paper/2507.01182/) (2025)
- [SynthDistill: Face Recognition with Knowledge Distillation from Synthetic Data](https://mlsanity.com/paper/2308.14852/) (2023)
- [Knowledge Distillation with Refined Logits](https://mlsanity.com/paper/2408.07703/) (2024)
- [Decoupled Global-Local Alignment for Improving Compositional Understanding](https://mlsanity.com/paper/2504.16801/) (2025)
- [The Role of Masking for Efficient Supervised Knowledge Distillation of Vision Transformers](https://mlsanity.com/paper/2302.10494/) (2023)

## Abstract (arXiv)

Most existing distillation methods ignore the flexible role of the temperature in the loss function and fix it as a hyper-parameter that can be decided by an inefficient grid search. In general, the temperature controls the discrepancy between two distributions and can faithfully determine the difficulty level of the distillation task. Keeping a constant temperature, i.e., a fixed level of task difficulty, is usually sub-optimal for a growing student during its progressive learning stages. In this paper, we propose a simple curriculum-based technique, termed Curriculum Temperature for Knowledge Distillation (CTKD), which controls the task difficulty level during the student's learning career through a dynamic and learnable temperature. Specifically, following an easy-to-hard curriculum, we gradually increase the distillation loss w.r.t. the temperature, leading to increased distillation difficulty in an adversarial manner. As an easy-to-use plug-in technique, CTKD can be seamlessly integrated into existing knowledge distillation frameworks and brings general improvements at a negligible additional computation cost. Extensive experiments on CIFAR-100, ImageNet-2012, and MS-COCO demonstrate the effectiveness of our method. Our code is available at https://github.com/zhengli97/CTKD.