A new benchmark for synthetic-to-real domain adaptation

Released in: Syn2Real: A New Benchmark for Synthetic-to-Real Visual Domain Adaptation



Unsupervised transfer of object recognition models from synthetic to real data is an important problem with many potential applications. The challenge is how to “adapt” a model trained on simulated images so that it performs well on real-world data without any additional supervision. Unfortunately, current benchmarks for this problem are limited in size and task diversity. In this paper, the authors present a new large-scale benchmark called Syn2Real, which consists of a synthetic domain rendered from 3D object models and two real-image domains containing the same object categories. The paper defines three related tasks on this benchmark: closed-set object classification, open-set object classification, and object detection. Evaluation of multiple state-of-the-art methods reveals a large gap in adaptation performance between the easier closed-set classification task and the more difficult open-set and detection tasks. The authors conclude that developing adaptation methods that work well across all three tasks presents a significant future challenge for syn2real domain transfer.


Year Released

Key Links & Stats


Syn2Real: A New Benchmark for Synthetic-to-Real Visual Domain Adaptation

ML Tasks

  1. Domain Adaptation
  2. Image Classification
  3. Object Detection
  4. Semantic Segmentation

ML Platform

  1. Not Applicable


  1. General
  2. Still Image


  1. General

CG Platform

  1. Not Applicable

Related organizations

Boston University

University of Tokyo

UC Berkeley