Self-Training and Adversarial Background Regularization for Unsupervised Domain Adaptive One-Stage Object Detection

Abstract

Deep learning-based object detectors have shown remarkable improvements. However, supervised learning-based methods perform poorly when the train data and the test data have different distributions. To address the issue, domain adaptation transfers knowledge from the label-sufficient domain (source domain) to the label-scarce domain (target domain). Self-training is one of the powerful ways to achieve domain adaptation since it helps class-wise domain adaptation. Unfortunately, a naive approach that utilizes pseudo-labels as ground-truth degenerates the performance due to incorrect pseudo-labels. In this paper, we introduce a weak self-training (WST) method and adversarial background score regularization (BSR) for domain adaptive one-stage object detection. WST diminishes the adverse effects of inaccurate pseudo-labels to stabilize the learning procedure. BSR helps the network extract discriminative features for target backgrounds to reduce the domain shift. Two components are complementary to each other as BSR enhances discrimination between foregrounds and backgrounds, whereas WST strengthen class-wise discrimination. Experimental results show that our approach effectively improves the performance of the one-stage object detection in unsupervised domain adaptation setting.

arXiv commentICCV 2019 (oral)

References in corpus (10)

• R-FCN: Object Detection via Region-based Fully Convolutional Networks
• Learning Transferable Features with Deep Adaptation Networks
• Conditional Adversarial Domain Adaptation
• CyCADA: Cycle-Consistent Adversarial Domain Adaptation
• Asymmetric Tri-training for Unsupervised Domain Adaptation
• A DIRT-T Approach to Unsupervised Domain Adaptation
• Self Paced Deep Learning for Weakly Supervised Object Detection
• Pseudo-Labeling Curriculum for Unsupervised Domain Adaptation
• Self-ensembling for visual domain adaptation
• Adaptive Semantic Segmentation with a Strategic Curriculum of Proxy Labels

Cited by in corpus (7)

• Decoupled Adaptation for Cross-Domain Object Detection
• On Universal Black-Box Domain Adaptation
• Spatial Attention Pyramid Network for Unsupervised Domain Adaptation
• Cross-Domain Document Object Detection: Benchmark Suite and Method
• Synergistic saliency and depth prediction for RGB-D saliency detection
• Exploring Data Aggregation and Transformations to Generalize across Visual Domains
• Channel-Temporal Attention for First-Person Video Domain Adaptation