Domain Adaptation Through Task Distillation

by   Brady Zhou, et al.

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.


page 2

page 5

page 7

page 8

page 12


Unsupervised Domain Adaptation for Visual Navigation

Advances in visual navigation methods have led to intelligent embodied n...

Localising In Complex Scenes Using Balanced Adversarial Adaptation

Domain adaptation and generative modelling have collectively mitigated t...

Domain Adaptation via Low-Rank Basis Approximation

Transfer learning focuses on the reuse of supervised learning models in ...

EPOpt: Learning Robust Neural Network Policies Using Model Ensembles

Sample complexity and safety are major challenges when learning policies...

Tackling Partial Domain Adaptation with Self-Supervision

Domain adaptation approaches have shown promising results in reducing th...

Online Domain Adaptation for Occupancy Mapping

Creating accurate spatial representations that take into account uncerta...

Code Repositories


Code for Domain Adaptation Through Task Distillation (ECCV 20)

view repo

Please sign up or login with your details

Forgot password? Click here to reset