# Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlooks

arXiv: https://arxiv.org/abs/2004.05937 · HTML: https://mlsanity.com/paper/2004.05937/

## Key facts

- Cited by 316 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Apr 2020.

## Built on by (most cited first, 30 of 316)

- [LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS](https://mlsanity.com/paper/2311.17245/) (2023)
- [Decoupled Knowledge Distillation](https://mlsanity.com/paper/2203.08679/) (2022)
- [Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining](https://mlsanity.com/paper/2302.02318/) (2023)
- [Student-Teacher Feature Pyramid Matching for Anomaly Detection](https://mlsanity.com/paper/2103.04257/) (2021)
- [Knowledge Distillation with the Reused Teacher Classifier](https://mlsanity.com/paper/2203.14001/) (2022)
- [NL4Opt Competition: Formulating Optimization Problems Based on Their Natural Language Descriptions](https://mlsanity.com/paper/2303.08233/) (2023)
- [Structured Pruning for Deep Convolutional Neural Networks: A survey](https://mlsanity.com/paper/2303.00566/) (2023)
- [Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis](https://mlsanity.com/paper/2312.08782/) (2023)
- [Logit Standardization in Knowledge Distillation](https://mlsanity.com/paper/2403.01427/) (2024)
- [PD-Quant: Post-Training Quantization based on Prediction Difference Metric](https://mlsanity.com/paper/2212.07048/) (2022)
- [R2L: Distilling Neural Radiance Field to Neural Light Field for Efficient Novel View Synthesis](https://mlsanity.com/paper/2203.17261/) (2022)
- [Survey on Knowledge Distillation for Large Language Models: Methods, Evaluation, and Application](https://mlsanity.com/paper/2407.01885/) (2024)
- [Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomy](https://mlsanity.com/paper/2305.06360/) (2023)
- [DeepReDuce: ReLU Reduction for Fast Private Inference](https://mlsanity.com/paper/2103.01396/) (2021)
- [A Fast Knowledge Distillation Framework for Visual Recognition](https://mlsanity.com/paper/2112.01528/) (2021)
- [EvDistill: Asynchronous Events to End-task Learning via Bidirectional Reconstruction-guided Cross-modal Knowledge Distillation](https://mlsanity.com/paper/2111.12341/) (2021)
- [Deep Learning for HDR Imaging: State-of-the-Art and Future Trends](https://mlsanity.com/paper/2110.10394/) (2021)
- [The Modality Focusing Hypothesis: Towards Understanding Crossmodal Knowledge Distillation](https://mlsanity.com/paper/2206.06487/) (2022)
- [Tiny Machine Learning: Progress and Futures](https://mlsanity.com/paper/2403.19076/) (2024)
- [Knowledge Distillation on Graphs: A Survey](https://mlsanity.com/paper/2302.00219/) (2023)
- [Learning Compatible Embeddings](https://mlsanity.com/paper/2108.01958/) (2021)
- [A Survey on Generative AI and LLM for Video Generation, Understanding, and Streaming](https://mlsanity.com/paper/2404.16038/) (2024)
- [A Good Student is Cooperative and Reliable: CNN-Transformer Collaborative Learning for Semantic Segmentation](https://mlsanity.com/paper/2307.12574/) (2023)
- [Dual Transfer Learning for Event-based End-task Prediction via Pluggable Event to Image Translation](https://mlsanity.com/paper/2109.01801/) (2021)
- [CLIP-TD: CLIP Targeted Distillation for Vision-Language Tasks](https://mlsanity.com/paper/2201.05729/) (2022)
- [Correlation-Decoupled Knowledge Distillation for Multimodal Sentiment Analysis with Incomplete Modalities](https://mlsanity.com/paper/2404.16456/) (2024)
- [Data-Free Knowledge Transfer: A Survey](https://mlsanity.com/paper/2112.15278/) (2021)
- [Distilled GPT for Source Code Summarization](https://mlsanity.com/paper/2308.14731/) (2023)
- [Federated Graph Semantic and Structural Learning](https://mlsanity.com/paper/2406.18937/) (2024)
- [Self-Distillation from the Last Mini-Batch for Consistency Regularization](https://mlsanity.com/paper/2203.16172/) (2022)

## Abstract (arXiv)

Deep neural models in recent years have been successful in almost every field, including extremely complex problem statements. However, these models are huge in size, with millions (and even billions) of parameters, thus demanding more heavy computation power and failing to be deployed on edge devices. Besides, the performance boost is highly dependent on redundant labeled data. To achieve faster speeds and to handle the problems caused by the lack of data, knowledge distillation (KD) has been proposed to transfer information learned from one model to another. KD is often characterized by the so-called `Student-Teacher' (S-T) learning framework and has been broadly applied in model compression and knowledge transfer. This paper is about KD and S-T learning, which are being actively studied in recent years. First, we aim to provide explanations of what KD is and how/why it works. Then, we provide a comprehensive survey on the recent progress of KD methods together with S-T frameworks typically for vision tasks. In general, we consider some fundamental questions that have been driving this research area and thoroughly generalize the research progress and technical details. Additionally, we systematically analyze the research status of KD in vision applications. Finally, we discuss the potentials and open challenges of existing methods and prospect the future directions of KD and S-T learning.