# MDFlow: Unsupervised Optical Flow Learning by Reliable Mutual Knowledge Distillation

arXiv: https://arxiv.org/abs/2211.06018 · HTML: https://mlsanity.com/paper/2211.06018/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in General knowledge distillation methods, one of 12 directions in Knowledge distillation.
- Builds on 50 of its 74 references that are in the map.
- First posted on arXiv 11 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 50)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer](https://mlsanity.com/paper/1612.03928/) (2016)
- [FlowNet: Learning Optical Flow with Convolutional Networks](https://mlsanity.com/paper/1504.06852/) (2015)
- [PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume](https://mlsanity.com/paper/1709.02371/) (2017)
- [The 2017 DAVIS Challenge on Video Object Segmentation](https://mlsanity.com/paper/1704.00675/) (2017)
- [A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation](https://mlsanity.com/paper/1512.02134/) (2015)
- [FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks](https://mlsanity.com/paper/1612.01925/) (2016)
- [Contrastive Representation Distillation](https://mlsanity.com/paper/1910.10699/) (2019)
- [Deep Mutual Learning](https://mlsanity.com/paper/1706.00384/) (2017)
- [Optical Flow Estimation using a Spatial Pyramid Network](https://mlsanity.com/paper/1611.00850/) (2016)
- [Learning to Estimate Hidden Motions with Global Motion Aggregation](https://mlsanity.com/paper/2104.02409/) (2021)
- [UnFlow: Unsupervised Learning of Optical Flow with a Bidirectional Census Loss](https://mlsanity.com/paper/1711.07837/) (2017)
- [Uncertainty Estimates and Multi-Hypotheses Networks for Optical Flow](https://mlsanity.com/paper/1802.07095/) (2018)
- [Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimation](https://mlsanity.com/paper/1904.05290/) (2019)
- [SelFlow: Self-Supervised Learning of Optical Flow](https://mlsanity.com/paper/1904.09117/) (2019)
- [What Matters in Unsupervised Optical Flow](https://mlsanity.com/paper/2006.04902/) (2020)
- [Learning by Analogy: Reliable Supervision from Transformations for Unsupervised Optical Flow Estimation](https://mlsanity.com/paper/2003.13045/) (2020)
- [MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask](https://mlsanity.com/paper/2003.10955/) (2020)
- [IFRNet: Intermediate Feature Refine Network for Efficient Frame Interpolation](https://mlsanity.com/paper/2205.14620/) (2022)
- [Novel Visual Category Discovery with Dual Ranking Statistics and Mutual Knowledge Distillation](https://mlsanity.com/paper/2107.03358/) (2021)
- [Mutual Graph Learning for Camouflaged Object Detection](https://mlsanity.com/paper/2104.02613/) (2021)
- [Back to Basics: Unsupervised Learning of Optical Flow via Brightness Constancy and Motion Smoothness](https://mlsanity.com/paper/1608.05842/) (2016)
- [Occlusion Aware Unsupervised Learning of Optical Flow](https://mlsanity.com/paper/1711.05890/) (2017)
- [Models Matter, So Does Training: An Empirical Study of CNNs for Optical Flow Estimation](https://mlsanity.com/paper/1809.05571/) (2018)
- [SMURF: Self-Teaching Multi-Frame Unsupervised RAFT with Full-Image Warping](https://mlsanity.com/paper/2105.07014/) (2021)
- [DDFlow: Learning Optical Flow with Unlabeled Data Distillation](https://mlsanity.com/paper/1902.09145/) (2019)
- [Displacement-Invariant Matching Cost Learning for Accurate Optical Flow Estimation](https://mlsanity.com/paper/2010.14851/) (2020)

## Built on by (most cited first, 10 of 10)

- [MotionGS: Exploring Explicit Motion Guidance for Deformable 3D Gaussian Splatting](https://mlsanity.com/paper/2410.07707/) (2024)
- [ADFactory: An Effective Framework for Generalizing Optical Flow with Nerf](https://mlsanity.com/paper/2311.04246/) (2023)
- [CNN-Transformer Rectified Collaborative Learning for Medical Image Segmentation](https://mlsanity.com/paper/2408.13698/) (2024)
- [Towards Better Data Exploitation in Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/2309.05254/) (2023)
- [Dynamic Frame Interpolation in Wavelet Domain](https://mlsanity.com/paper/2309.03508/) (2023)
- [Self-Assessed Generation: Trustworthy Label Generation for Optical Flow and Stereo Matching in Real-world](https://mlsanity.com/paper/2410.10453/) (2024)
- [Instance-aware Model Ensemble With Distillation For Unsupervised Domain Adaptation](https://mlsanity.com/paper/2211.08106/) (2022)
- [Latent Graph Attention for Enhanced Spatial Context](https://mlsanity.com/paper/2307.04149/) (2023)
- [HKT: A Biologically Inspired Framework for Modular Hereditary Knowledge Transfer in Neural Networks](https://mlsanity.com/paper/2508.09743/) (2025)
- [DispFlow-GS: Displacement Flow Supervision with Motion Disentangling for Monocular Deformable 3D Gaussian Splatting](https://mlsanity.com/paper/2609.36940/) (2026)

## Abstract (arXiv)

Recent works have shown that optical flow can be learned by deep networks from unlabelled image pairs based on brightness constancy assumption and smoothness prior. Current approaches additionally impose an augmentation regularization term for continual self-supervision, which has been proved to be effective on difficult matching regions. However, this method also amplify the inevitable mismatch in unsupervised setting, blocking the learning process towards optimal solution. To break the dilemma, we propose a novel mutual distillation framework to transfer reliable knowledge back and forth between the teacher and student networks for alternate improvement. Concretely, taking estimation of off-the-shelf unsupervised approach as pseudo labels, our insight locates at defining a confidence selection mechanism to extract relative good matches, and then add diverse data augmentation for distilling adequate and reliable knowledge from teacher to student. Thanks to the decouple nature of our method, we can choose a stronger student architecture for sufficient learning. Finally, better student prediction is adopted to transfer knowledge back to the efficient teacher without additional costs in real deployment. Rather than formulating it as a supervised task, we find that introducing an extra unsupervised term for multi-target learning achieves best final results. Extensive experiments show that our approach, termed MDFlow, achieves state-of-the-art real-time accuracy and generalization ability on challenging benchmarks. Code is available at https://github.com/ltkong218/MDFlow.