# Domain Adaptation Through Task Distillation

arXiv: https://arxiv.org/abs/2008.11911 · HTML: https://mlsanity.com/paper/2008.11911/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Aug 2020.

## Built on by (most cited first, 11 of 11)

- [Source-Free Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2103.16372/) (2021)
- [A Comprehensive Survey on Source-free Domain Adaptation](https://mlsanity.com/paper/2302.11803/) (2023)
- [Learning Student-Friendly Teacher Networks for Knowledge Distillation](https://mlsanity.com/paper/2102.07650/) (2021)
- [SECANT: Self-Expert Cloning for Zero-Shot Generalization of Visual Policies](https://mlsanity.com/paper/2106.09678/) (2021)
- [Divide to Adapt: Mitigating Confirmation Bias for Domain Adaptation of Black-Box Predictors](https://mlsanity.com/paper/2205.14467/) (2022)
- [Towards Data-Free Domain Generalization](https://mlsanity.com/paper/2110.04545/) (2021)
- [Unsupervised Domain Adaptation via Distilled Discriminative Clustering](https://mlsanity.com/paper/2302.11984/) (2023)
- [Robust Navigation with Cross-Modal Fusion and Knowledge Transfer](https://mlsanity.com/paper/2309.13266/) (2023)
- [Learning Cascaded Detection Tasks with Weakly-Supervised Domain Adaptation](https://mlsanity.com/paper/2107.04523/) (2021)
- [Efficient Training of Generalizable Visuomotor Policies via Control-Aware Augmentation](https://mlsanity.com/paper/2401.09258/) (2024)
- [Neural network task specialization via domain constraining](https://mlsanity.com/paper/2504.19592/) (2025)

## Abstract (arXiv)

Deep networks devour millions of precisely annotated images to build their complex and powerful representations. Unfortunately, tasks like autonomous driving have virtually no real-world training data. Repeatedly crashing a car into a tree is simply too expensive. The commonly prescribed solution is simple: learn a representation in simulation and transfer it to the real world. However, this transfer is challenging since simulated and real-world visual experiences vary dramatically. Our core observation is that for certain tasks, such as image recognition, datasets are plentiful. They exist in any interesting domain, simulated or real, and are easy to label and extend. We use these recognition datasets to link up a source and target domain to transfer models between them in a task distillation framework. Our method can successfully transfer navigation policies between drastically different simulators: ViZDoom, SuperTuxKart, and CARLA. Furthermore, it shows promising results on standard domain adaptation benchmarks.