Progressive Graph Learning for Open-Set Domain Adaptation

Abstract

Domain shift is a fundamental problem in visual recognition which typically arises when the source and target data follow different distributions. The existing domain adaptation approaches which tackle this problem work in the closed-set setting with the assumption that the source and the target data share exactly the same classes of objects. In this paper, we tackle a more realistic problem of open-set domain shift where the target data contains additional classes that are not present in the source data. More specifically, we introduce an end-to-end Progressive Graph Learning (PGL) framework where a graph neural network with episodic training is integrated to suppress underlying conditional shift and adversarial learning is adopted to close the gap between the source and target distributions. Compared to the existing open-set adaptation approaches, our approach guarantees to achieve a tighter upper bound of the target error. Extensive experiments on three standard open-set benchmarks evidence that our approach significantly outperforms the state-of-the-arts in open-set domain adaptation.

Cited by in corpus (7)

• A Survey on Deep Domain Adaptation for LiDAR Perception
• Relation Matters: Foreground-aware Graph-based Relational Reasoning for Domain Adaptive Object Detection
• Domain-adaptive Message Passing Graph Neural Network
• Conditional Extreme Value Theory for Open Set Video Domain Adaptation
• Learning to Diversify for Single Domain Generalization
• Entropy-Based Uncertainty Calibration for Generalized Zero-Shot Learning
• Attribute-aware Explainable Complementary Clothing Recommendation