UDA4Inst: Unsupervised Domain Adaptation for Instance Segmentation

TL;DR

UDA4Inst is a novel framework that significantly improves unsupervised domain adaptation for instance segmentation in autonomous driving by leveraging semantic grouping and bidirectional data mixing.

Contribution

It introduces Semantic Category Training and Bidirectional Mixing Training to enhance pseudo-label quality and domain generalization in instance segmentation.

Findings

Sets new state-of-the-art on SYNTHIA->Cityscapes benchmark (mAP 31.3)

Achieves effective adaptation on UrbanSyn and Synscapes datasets

Demonstrates improved generalization across diverse urban datasets.

Abstract

Instance segmentation is crucial for autonomous driving, but is hindered by the lack of annotated real-world data due to expensive labeling costs. Unsupervised Domain Adaptation (UDA) offers a solution by transferring knowledge from labeled synthetic data to unlabeled real-world data. While UDA methods for synthetic to real-world domains (synth-to-real) excel in tasks such as semantic segmentation and object detection, their application to instance segmentation for autonomous driving remains underexplored and often relies on suboptimal baselines. We introduce UDA4Inst, a powerful framework for synth-to-real UDA in instance segmentation. Our framework enhances instance segmentation through Semantic Category Training and Bidirectional Mixing Training. Semantic Category Training groups semantically related classes for separate training, improving pseudo-label quality and segmentation accuracy. Bidirectional Mixing Training combines instance-wise and patch-wise data mixing, creating coherent composites that enhance generalization across domains. Extensive experiments show UDA4Inst sets a new state-of-the-art on the SYNTHIA-> Cityscapes benchmark (mAP 31.3) and introduces results on novel datasets, using UrbanSyn and Synscapes as sources and Cityscapes and KITTI360 as targets. Code and models are available at https://github.com/gyc-code/UDA4Inst.