Diversify and Match: A Domain Adaptive Representation Learning Paradigm for Object Detection
This work addresses domain adaptation for object detection, which is crucial for deploying models in real-world scenarios with varying data distributions, representing a novel hybrid approach rather than a foundational breakthrough.
The paper tackles the problem of imperfect translation and source-biased discriminativity in unsupervised domain adaptation for object detection by introducing a two-stage approach with domain diversification and multi-domain-invariant representation learning, achieving a 3% to 11% improvement in mean average precision over state-of-the-art methods.
We introduce a novel unsupervised domain adaptation approach for object detection. We aim to alleviate the imperfect translation problem of pixel-level adaptations, and the source-biased discriminativity problem of feature-level adaptations simultaneously. Our approach is composed of two stages, i.e., Domain Diversification (DD) and Multi-domain-invariant Representation Learning (MRL). At the DD stage, we diversify the distribution of the labeled data by generating various distinctive shifted domains from the source domain. At the MRL stage, we apply adversarial learning with a multi-domain discriminator to encourage feature to be indistinguishable among the domains. DD addresses the source-biased discriminativity, while MRL mitigates the imperfect image translation. We construct a structured domain adaptation framework for our learning paradigm and introduce a practical way of DD for implementation. Our method outperforms the state-of-the-art methods by a large margin of 3%~11% in terms of mean average precision (mAP) on various datasets.