# Keyframe-Focused Visual Imitation Learning

arXiv: https://arxiv.org/abs/2106.06452 · HTML: https://mlsanity.com/paper/2106.06452/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Placed in Robot manipulation imitation learning, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 24 of its 42 references that are in the map.
- First posted on arXiv 11 Jun 2021.

## Placed in

- Offline RL and imitation learning from data / [Robot manipulation imitation learning](https://mlsanity.com/offlinerl/robot-manipulation-imitation-learning/)

## Builds on (most cited first, 24 of 24)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Trust Region Policy Optimization](https://mlsanity.com/paper/1502.05477/) (2015)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [End to End Learning for Self-Driving Cars](https://mlsanity.com/paper/1604.07316/) (2016)
- [Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss](https://mlsanity.com/paper/1906.07413/) (2019)
- [Decoupling Representation and Classifier for Long-Tailed Recognition](https://mlsanity.com/paper/1910.09217/) (2019)
- [Recognition in Terra Incognita](https://mlsanity.com/paper/1807.04975/) (2018)
- [End-to-end Driving via Conditional Imitation Learning](https://mlsanity.com/paper/1710.02410/) (2017)
- [An Algorithmic Perspective on Imitation Learning](https://mlsanity.com/paper/1811.06711/) (2018)
- [BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition](https://mlsanity.com/paper/1912.02413/) (2019)
- [ChauffeurNet: Learning to Drive by Imitating the Best and Synthesizing the Worst](https://mlsanity.com/paper/1812.03079/) (2018)
- [Learning by Cheating](https://mlsanity.com/paper/1912.12294/) (2019)
- [Exploring the Limitations of Behavior Cloning for Autonomous Driving](https://mlsanity.com/paper/1904.08980/) (2019)
- [Causal Confusion in Imitation Learning](https://mlsanity.com/paper/1905.11979/) (2019)
- [DART: Noise Injection for Robust Imitation Learning](https://mlsanity.com/paper/1703.09327/) (2017)
- [Deeply AggreVaTeD: Differentiable Imitation Learning for Sequential Prediction](https://mlsanity.com/paper/1703.01030/) (2017)
- [Fighting Copycat Agents in Behavioral Cloning from Observation Histories](https://mlsanity.com/paper/2010.14876/) (2020)
- [Class Rectification Hard Mining for Imbalanced Deep Learning](https://mlsanity.com/paper/1712.03162/) (2017)
- [An Evaluation of Change Point Detection Algorithms](https://mlsanity.com/paper/2003.06222/) (2020)
- [Monocular Plan View Networks for Autonomous Driving](https://mlsanity.com/paper/1905.06937/) (2019)

## Built on by (most cited first, 25 of 25)

- [End-to-end Autonomous Driving: Challenges and Frontiers](https://mlsanity.com/paper/2306.16927/) (2023)
- [TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving](https://mlsanity.com/paper/2205.15997/) (2022)
- [Vision-based Manipulation from Single Human Video with Open-World Object Graphs](https://mlsanity.com/paper/2405.20321/) (2024)
- [A Survey on Causal Reinforcement Learning](https://mlsanity.com/paper/2302.05209/) (2023)
- [ContextVLA: Vision-Language-Action Model with Amortized Multi-Frame Context](https://mlsanity.com/paper/2510.04246/) (2025)
- [Sequence Model Imitation Learning with Unobserved Contexts](https://mlsanity.com/paper/2208.02225/) (2022)
- [Learning Long-Context Diffusion Policies via Past-Token Prediction](https://mlsanity.com/paper/2505.09561/) (2025)
- [RLDX-1 Technical Report](https://mlsanity.com/paper/2605.03269/) (2026)
- [BPP: Long-Context Robot Imitation Learning by Focusing on Key History Frames](https://mlsanity.com/paper/2602.15010/) (2026)
- [Fighting Fire with Fire: Avoiding DNN Shortcuts through Priming](https://mlsanity.com/paper/2206.10816/) (2022)
- [Resolving Copycat Problems in Visual Imitation Learning via Residual Action Prediction](https://mlsanity.com/paper/2207.09705/) (2022)
- [Domain Adaptive Imitation Learning with Visual Observation](https://mlsanity.com/paper/2312.00548/) (2023)
- [VIEW: Visual Imitation Learning with Waypoints](https://mlsanity.com/paper/2404.17906/) (2024)
- [Efficient Long-Horizon Vision-Language-Action Models via Static-Dynamic Disentanglement](https://mlsanity.com/paper/2602.03983/) (2026)
- [AutoFocus-IL: VLM-based Saliency Maps for Data-Efficient Visual Imitation Learning without Extra Human Annotations](https://mlsanity.com/paper/2511.18617/) (2025)
- [Can Active Sampling Reduce Causal Confusion in Offline Reinforcement Learning?](https://mlsanity.com/paper/2312.17168/) (2023)
- [A Comprehensive Review of 3D Object Detection in Autonomous Driving: Technological Advances and Future Directions](https://mlsanity.com/paper/2408.16530/) (2024)
- [AEGIS: Human Attention-based Explainable Guidance for Intelligent Vehicle Systems](https://mlsanity.com/paper/2504.05950/) (2025)
- [A Review of Learning-Based Motion Planning: Toward a Data-Driven Optimal Control Approach](https://mlsanity.com/paper/2512.11944/) (2025)
- [SynthICL: Scalable In-context Imitation Learning with Synthetic Data](https://mlsanity.com/paper/2606.08154/) (2026)
- [Visual Imitation Learning with Calibrated Contrastive Representation](https://mlsanity.com/paper/2401.11396/) (2024)
- [End-to-end Autonomous Vehicle Following System using Monocular Fisheye Camera](https://mlsanity.com/paper/2511.19011/) (2025)
- [SkiP: When to Skip and When to Refine for Efficient Robot Manipulation](https://mlsanity.com/paper/2605.15536/) (2026)
- [Critical Interval MSE: Toward Reliable Offline Validation for Robot Manipulation Policies](https://mlsanity.com/paper/2606.29898/) (2026)
- [InfraVLA: Extending Vision-Language-Action Navigation with Infrastructure Cameras](https://mlsanity.com/paper/2609.33647/) (2026)

## Abstract (arXiv)

Imitation learning trains control policies by mimicking pre-recorded expert demonstrations. In partially observable settings, imitation policies must rely on observation histories, but many seemingly paradoxical results show better performance for policies that only access the most recent observation. Recent solutions ranging from causal graph learning to deep information bottlenecks have shown promising results, but failed to scale to realistic settings such as visual imitation. We propose a solution that outperforms these prior approaches by upweighting demonstration keyframes corresponding to expert action changepoints. This simple approach easily scales to complex visual imitation settings. Our experimental results demonstrate consistent performance improvements over all baselines on image-based Gym MuJoCo continuous control tasks. Finally, on the CARLA photorealistic vision-based urban driving simulator, we resolve a long-standing issue in behavioral cloning for driving by demonstrating effective imitation from observation histories. Supplementary materials and code at: urlhttps://tinyurl.com/imitation-keyframes.