Unsupervised Domain Adaptation for Object Detection via Cross-Domain Semi-Supervised Learning

Abstract

Current state-of-the-art object detectors can have significant performance drop when deployed in the wild due to domain gaps with training data. Unsupervised Domain Adaptation (UDA) is a promising approach to adapt models for new domains/environments without any expensive label cost. However, without ground truth labels, most prior works on UDA for object detection tasks can only perform coarse image-level and/or feature-level adaptation by using adversarial learning methods. In this work, we show that such adversarial-based methods can only reduce the domain style gap, but cannot address the domain content distribution gap that is shown to be important for object detectors. To overcome this limitation, we propose the Cross-Domain Semi-Supervised Learning (CDSSL) framework by leveraging high-quality pseudo labels to learn better representations from the target domain directly. To enable SSL for cross-domain object detection, we propose fine-grained domain transfer, progressive-confidence-based label sharpening and imbalanced sampling strategy to address two challenges: (i) non-identical distribution between source and target domain data, (ii) error amplification/accumulation due to noisy pseudo labeling on the target domain. Experiment results show that our proposed approach consistently achieves new state-of-the-art performance (2.2% - 9.5% better than prior best work on mAP) under various domain gap scenarios. The code will be released.

Accepted in WACV'2022

References in corpus (9)

• Deep Domain Confusion: Maximizing for Domain Invariance
• Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
• Semi-Supervised Learning with Deep Generative Models
• Semantic Foggy Scene Understanding with Synthetic Data
• Unsupervised Domain Adaptation with Residual Transfer Networks
• FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
• CyCADA: Cycle-Consistent Adversarial Domain Adaptation
• Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenes
• Progressive Domain Adaptation for Object Detection

Cited by in corpus (6)

• Mutually improved endoscopic image synthesis and landmark detection in unpaired image-to-image translation
• Deep Domain Adaptive Object Detection: a Survey
• A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets
• Cut-and-Paste Dataset Generation for Balancing Domain Gaps in Object Instance Detection
• A Multi Camera Unsupervised Domain Adaptation Pipeline for Object Detection in Cultural Sites through Adversarial Learning and Self-Training
• Spectral Unsupervised Domain Adaptation for Visual Recognition