# Optical Flow Training under Limited Label Budget via Active Learning

arXiv: https://arxiv.org/abs/2203.05053 · HTML: https://mlsanity.com/paper/2203.05053/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 62 references that are in the map.
- First posted on arXiv 9 Mar 2022.

## Builds on (most cited first, 30 of 37)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [FlowNet: Learning Optical Flow with Convolutional Networks](https://mlsanity.com/paper/1504.06852/) (2015)
- [Temporal Ensembling for Semi-Supervised Learning](https://mlsanity.com/paper/1610.02242/) (2016)
- [PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume](https://mlsanity.com/paper/1709.02371/) (2017)
- [Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning](https://mlsanity.com/paper/1704.03976/) (2017)
- [A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation](https://mlsanity.com/paper/1512.02134/) (2015)
- [Deep Bayesian Active Learning with Image Data](https://mlsanity.com/paper/1703.02910/) (2017)
- [Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learning](https://mlsanity.com/paper/1606.04586/) (2016)
- [Optical Flow Estimation using a Spatial Pyramid Network](https://mlsanity.com/paper/1611.00850/) (2016)
- [GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose](https://mlsanity.com/paper/1803.02276/) (2018)
- [Structured Knowledge Distillation for Dense Prediction](https://mlsanity.com/paper/1903.04197/) (2019)
- [Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation](https://mlsanity.com/paper/1805.09806/) (2018)
- [UnFlow: Unsupervised Learning of Optical Flow with a Bidirectional Census Loss](https://mlsanity.com/paper/1711.07837/) (2017)
- [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)
- [Flow-edge Guided Video Completion](https://mlsanity.com/paper/2009.01835/) (2020)
- [Uncertainty-guided Continual Learning with Bayesian Neural Networks](https://mlsanity.com/paper/1906.02425/) (2019)
- [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)
- [ViewAL: Active Learning with Viewpoint Entropy for Semantic Segmentation](https://mlsanity.com/paper/1911.11789/) (2019)
- [Active Learning for Deep Object Detection via Probabilistic Modeling](https://mlsanity.com/paper/2103.16130/) (2021)
- [SMURF: Self-Teaching Multi-Frame Unsupervised RAFT with Full-Image Warping](https://mlsanity.com/paper/2105.07014/) (2021)
- [Occlusions, Motion and Depth Boundaries with a Generic Network for Disparity, Optical Flow or Scene Flow Estimation](https://mlsanity.com/paper/1808.01838/) (2018)
- [CEREALS - Cost-Effective REgion-based Active Learning for Semantic Segmentation](https://mlsanity.com/paper/1810.09726/) (2018)

## Built on by (most cited first, 14 of 14)

- [CentaurEval: Benchmarking Human-in-the-Loop Value in Agentic Coding](https://mlsanity.com/paper/2512.04111/) (2025)
- [Cross-Attention Transformer for Video Interpolation](https://mlsanity.com/paper/2207.04132/) (2022)
- [Self-supervised AutoFlow](https://mlsanity.com/paper/2212.01762/) (2022)
- [SemARFlow: Injecting Semantics into Unsupervised Optical Flow Estimation for Autonomous Driving](https://mlsanity.com/paper/2303.06209/) (2023)
- [UnSAMFlow: Unsupervised Optical Flow Guided by Segment Anything Model](https://mlsanity.com/paper/2405.02608/) (2024)
- [Unsupervised Flow Refinement near Motion Boundaries](https://mlsanity.com/paper/2208.02305/) (2022)
- [TRACER: Token ReAssignment for Concept ERasure in Generative Recommendation](https://mlsanity.com/paper/2606.07688/) (2026)
- [UFD-PRiME: Unsupervised Joint Learning of Optical Flow and Stereo Depth through Pixel-Level Rigid Motion Estimation](https://mlsanity.com/paper/2310.04712/) (2023)
- [Decomposition Sampling for Efficient Region Annotations in Active Learning](https://mlsanity.com/paper/2512.07606/) (2025)
- [Triangular Consistency as a Universal Constraint for Learning Optical Flow](https://mlsanity.com/paper/2606.19938/) (2026)
- [Evaluating the effect of data augmentation and BALD heuristics on distillation of Semantic-KITTI dataset](https://mlsanity.com/paper/2302.10679/) (2023)
- [GenOpticalFlow: A Generative Approach to Unsupervised Optical Flow Learning](https://mlsanity.com/paper/2603.22270/) (2026)
- [U2Flow: Uncertainty-Aware Unsupervised Optical Flow Estimation](https://mlsanity.com/paper/2604.10056/) (2026)
- [From Non-Convex Self-Concordant Regularization to Scalable Quasi-Newton Training of PINNs](https://mlsanity.com/paper/2608.04206/) (2026)

## Abstract (arXiv)

Supervised training of optical flow predictors generally yields better accuracy than unsupervised training. However, the improved performance comes at an often high annotation cost. Semi-supervised training trades off accuracy against annotation cost. We use a simple yet effective semi-supervised training method to show that even a small fraction of labels can improve flow accuracy by a significant margin over unsupervised training. In addition, we propose active learning methods based on simple heuristics to further reduce the number of labels required to achieve the same target accuracy. Our experiments on both synthetic and real optical flow datasets show that our semi-supervised networks generally need around 50% of the labels to achieve close to full-label accuracy, and only around 20% with active learning on Sintel. We also analyze and show insights on the factors that may influence active learning performance. Code is available at https://github.com/duke-vision/optical-flow-active-learning-release.