Syn2Real: A New Benchmark forSynthetic-to-Real Visual Domain Adaptation

Abstract

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, we 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. We define three related tasks on this benchmark: closed-set object classification, open-set object classification, and object detection. Our 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. We conclude that developing adaptation methods that work well across all three tasks presents a significant future challenge for syn2real domain transfer.

References in corpus (12)

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Learning Transferable Features with Deep Adaptation Networks
• The Cityscapes Dataset for Semantic Urban Scene Understanding
• Equivalence of distance-based and RKHS-based statistics in hypothesis testing
• YOLO9000: Better, Faster, Stronger
• Aggregated Residual Transformations for Deep Neural Networks
• Domain Adaptation for Visual Applications: A Comprehensive Survey
• CARLA: An Open Urban Driving Simulator
• Playing for Data: Ground Truth from Computer Games
• A Large Dataset of Object Scans
• Return of Frustratingly Easy Domain Adaptation
• Open Set Domain Adaptation by Backpropagation

Cited by in corpus (16)

• Unsupervised Multi-Class Domain Adaptation: Theory, Algorithms, and Practice
• Moment Matching for Multi-Source Domain Adaptation
• Exploring Object Relation in Mean Teacher for Cross-Domain Detection
• A Review of Single-Source Deep Unsupervised Visual Domain Adaptation
• Adapting Object Detectors with Conditional Domain Normalization
• Temporal Attentive Alignment for Large-Scale Video Domain Adaptation
• Deep Domain Adaptive Object Detection: a Survey
• A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets
• Known-class Aware Self-ensemble for Open Set Domain Adaptation
• Discriminative Adversarial Domain Adaptation
• SPEED+: Next-Generation Dataset for Spacecraft Pose Estimation across Domain Gap
• Exploring Category-Agnostic Clusters for Open-Set Domain Adaptation
• DEPARA: Deep Attribution Graph for Deep Knowledge Transferability
• Domain2Vec: Domain Embedding for Unsupervised Domain Adaptation
• Adversarial Domain Randomization
• ADeLA: Automatic Dense Labeling with Attention for Viewpoint Adaptation in Semantic Segmentation