Oral
CyCADA: Cycle-Consistent Adversarial Domain Adaptation
Judy Hoffman · Eric Tzeng · Taesung Park · Jun-Yan Zhu · Philip Isola · Kate Saenko · Alexei Efros · Trevor Darrell

Fri Jul 13th 11:30 -- 11:40 AM @ A3

Domain adaptation is critical for success in new, unseen environments.Adversarial adaptation models have shown tremendous progress towards adapting to new environments by focusing either on discovering domain invariant representations or by mapping between unpaired image domains. While feature space methods are difficult to interpret and sometimes fail to capture pixel-level and low-level domain shifts, image space methods sometimes fail to incorporate high level semantic knowledge relevant for the end task.We propose a model which adapts between domains using both generative image space alignment and latent representation space alignment. Our approach, Cycle-Consistent Adversarial Domain Adaptation (CyCADA), guides transfer between domains according to a specific discriminatively trained task and avoids divergence by enforcing consistency of the relevant semantics before and after adaptation.We evaluate our method on a variety of visual recognition and prediction settings, including digit classification and semantic segmentation of road scenes, advancing state-of-the-art performance for unsupervised adaptation from synthetic to real world driving domains.

Author Information

Judy Hoffman (UC Berkeley and Georgia Tech)
Eric Tzeng (UC Berkeley)
Taesung Park (UC Berkeley)
Jun-Yan Zhu (MIT)

Jun-Yan Zhu received his B.E in Computer Sciences from Tsinghua University in 2012. He obtained his Ph.D. in Electrical Engineering and Computer Sciences from UC Berkeley in 2017 supervised by Alexei A. Efros, after spending five years at CMU and UC Berkeley. His Ph.D. work was supported by a Facebook Fellowship and awarded the 2017 David J. Sakrison Memorial Prize for the outstanding doctoral research from Berkeley EECS. Jun-Yan is currently a postdoctoral researcher at MIT CSAIL.

Philip Isola (UC Berkeley)
Kate Saenko (Boston University)
Alexei Efros (UC Berkeley)
Prof. Darrell (University of California at Berkeley)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors