In the context of single-source domain generalized object detection, the diversification of the source domain is of paramount importance, as it significantly influences the model’s generalization ability across different target domains. Existing data augmentation strategies for single-source domain generalization often overlook the preservation of foreground features in the source domain during the augmentation process, inevitably compromising the effectiveness and integrity of source-domain foreground information.To address this issue, we propose an effective data augmentation method called statistical-driven adaptive piecewise mapping (SDAPM), which automatically adjusts mapping parameters based on image statistical features to maximally mitigate the detail loss in source-domain data caused by diversification operations during the augmentation stage. Additionally, we introduce a dynamic heterogeneous domain perturbation generator (DHDPG) built upon SDAPM, which simulates various types of domain shifts under natural weather conditions. Both SDAPM and DHDPG are designed to mimic domain shift phenomena while preserving source domain foreground information, enabling the detector to learn critical foreground domain-invariant factors and enhancing its performance robustness under harsh scenarios.On the multi-weather dataset and the large CityScapes-C dataset, the proposed method achieved significant improvements of 7.6% and 9.8%, respectively, compared with the baseline method—this highlights its stronger generalization ability in practical applications. • We propose an adaptive method that enhances images based on their statistical features. • A new module mimics weather effects while preserving object details during training. • Our approach boosts detection by over 11% in harsh scenes like rainy nights. • The method improves both robustness and accuracy without using target domain data.
Lu et al. (Fri,) studied this question.