Uncertainty-Aware Unsupervised Domain Adaptation in Object Detection
This work addresses domain shift in object detection for applications like autonomous driving, but it is incremental as it builds on existing adversarial learning frameworks.
The paper tackles the problem of adversarial learning impairing well-aligned samples in unsupervised domain adaptive object detection by proposing an uncertainty-aware network that adaptively aligns samples based on their alignment quality, achieving superior performance on four datasets compared to state-of-the-art methods.
Unsupervised domain adaptive object detection aims to adapt detectors from a labelled source domain to an unlabelled target domain. Most existing works take a two-stage strategy that first generates region proposals and then detects objects of interest, where adversarial learning is widely adopted to mitigate the inter-domain discrepancy in both stages. However, adversarial learning may impair the alignment of well-aligned samples as it merely aligns the global distributions across domains. To address this issue, we design an uncertainty-aware domain adaptation network (UaDAN) that introduces conditional adversarial learning to align well-aligned and poorly-aligned samples separately in different manners. Specifically, we design an uncertainty metric that assesses the alignment of each sample and adjusts the strength of adversarial learning for well-aligned and poorly-aligned samples adaptively. In addition, we exploit the uncertainty metric to achieve curriculum learning that first performs easier image-level alignment and then more difficult instance-level alignment progressively. Extensive experiments over four challenging domain adaptive object detection datasets show that UaDAN achieves superior performance as compared with state-of-the-art methods.