# Multi-Teacher Knowledge Distillation with Reinforcement Learning for Visual Recognition

arXiv: https://arxiv.org/abs/2502.18510 · HTML: https://mlsanity.com/paper/2502.18510/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Placed in General knowledge distillation methods, one of 12 directions in Knowledge distillation.
- Builds on 38 of its 53 references that are in the map.
- First posted on arXiv 22 Feb 2025.

## Placed in

- Knowledge distillation / [General knowledge distillation methods](https://mlsanity.com/distill/general-knowledge-distillation-methods/)
- Deep reinforcement learning methods / [RL training of language and agent models](https://mlsanity.com/deeprl/rl-training-of-language-and-agent-models/)

## Builds on (most cited first, 30 of 38)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [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)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [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)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [Deep Reinforcement Learning with Double Q-learning](https://mlsanity.com/paper/1509.06461/) (2015)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design](https://mlsanity.com/paper/1807.11164/) (2018)
- [Designing Network Design Spaces](https://mlsanity.com/paper/2003.13678/) (2020)
- [On the Efficacy of Knowledge Distillation](https://mlsanity.com/paper/1910.01348/) (2019)
- [Knowledge Distillation from A Stronger Teacher](https://mlsanity.com/paper/2205.10536/) (2022)
- [Cross-Image Relational Knowledge Distillation for Semantic Segmentation](https://mlsanity.com/paper/2204.06986/) (2022)
- [A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multimodal](https://mlsanity.com/paper/2212.05767/) (2022)
- [CLIP-KD: An Empirical Study of CLIP Model Distillation](https://mlsanity.com/paper/2307.12732/) (2023)
- [Adaptive Multi-Teacher Multi-level Knowledge Distillation](https://mlsanity.com/paper/2103.04062/) (2021)
- [Reinforced Multi-Teacher Selection for Knowledge Distillation](https://mlsanity.com/paper/2012.06048/) (2020)
- [Hierarchical Self-supervised Augmented Knowledge Distillation](https://mlsanity.com/paper/2107.13715/) (2021)
- [Confidence-Aware Multi-Teacher Knowledge Distillation](https://mlsanity.com/paper/2201.00007/) (2021)

## Built on by (most cited first, 16 of 16)

- [Frequency-Aligned Knowledge Distillation for Lightweight Spatiotemporal Forecasting](https://mlsanity.com/paper/2507.02939/) (2025)
- [Masking Teacher and Reinforcing Student for Distilling Vision-Language Models](https://mlsanity.com/paper/2512.22238/) (2025)
- [DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer](https://mlsanity.com/paper/2505.15133/) (2025)
- [HeaPA: Difficulty-Aware Heap Sampling and On-Policy Query Augmentation for LLM Reinforcement Learning](https://mlsanity.com/paper/2601.22448/) (2026)
- [On the Fast Adaptation of Delayed Clients in Decentralized Federated Learning: A Centroid-Aligned Distillation Approach](https://mlsanity.com/paper/2508.02993/) (2025)
- [Adaptive Weighting in Knowledge Distillation: An Axiomatic Framework for Multi-Scale Teacher Ensemble Optimization](https://mlsanity.com/paper/2601.17910/) (2026)
- [When to Trust, How to Distill: Multi-Foundation Model Guidance for Lightweight, Robust Scientific Time Series Forecasting](https://mlsanity.com/paper/2606.19363/) (2026)
- [AnyBody: Free-Form Whole-Body Humanoid Control from Arbitrary Keypoint Guidance](https://mlsanity.com/paper/2606.29209/) (2026)
- [CAST: Contrastive Adaptation and Distillation for Semi-Supervised Instance Segmentation](https://mlsanity.com/paper/2505.21904/) (2025)
- [Faster and Better: Reinforced Collaborative Distillation and Self-Learning for Infrared-Visible Image Fusion](https://mlsanity.com/paper/2509.02424/) (2025)
- [Powerful Teachers Matter: Text-Guided Multi-view Knowledge Distillation with Visual Prior Enhancement](https://mlsanity.com/paper/2603.24208/) (2026)
- [Training a Student Expert via Semi-Supervised Foundation Model Distillation](https://mlsanity.com/paper/2604.03841/) (2026)
- [KD-MARL: Resource-Aware Knowledge Distillation in Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2604.06691/) (2026)
- [Unsupervised Collaborative Domain Adaptation for Driving Scene Parsing](https://mlsanity.com/paper/2606.01818/) (2026)
- [UMSS: Towards Unsupervised Multi-modal Semantic Segmentation](https://mlsanity.com/paper/2607.12372/) (2026)
- [Discovering and Preserving Category Correlation Knowledge via Adaptive Reciprocal Knowledge Distillation](https://mlsanity.com/paper/2609.13199/) (2026)

## Abstract (arXiv)

Multi-teacher Knowledge Distillation (KD) transfers diverse knowledge from a teacher pool to a student network. The core problem of multi-teacher KD is how to balance distillation strengths among various teachers. Most existing methods often develop weighting strategies from an individual perspective of teacher performance or teacher-student gaps, lacking comprehensive information for guidance. This paper proposes Multi-Teacher Knowledge Distillation with Reinforcement Learning (MTKD-RL) to optimize multi-teacher weights. In this framework, we construct both teacher performance and teacher-student gaps as state information to an agent. The agent outputs the teacher weight and can be updated by the return reward from the student. MTKD-RL reinforces the interaction between the student and teacher using an agent in an RL-based decision mechanism, achieving better matching capability with more meaningful weights. Experimental results on visual recognition tasks, including image classification, object detection, and semantic segmentation tasks, demonstrate that MTKD-RL achieves state-of-the-art performance compared to the existing multi-teacher KD works.